© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 7368
    Prev
    Next
    INDEX
    Explanations

    numerical values representing years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    years in the 1900s and 2000s, particularly dates from the mid-to-late 20th century.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of four-digit years and dates, especially 19xx/20xx years.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insky
    -0.15
    voje
    -0.15
    olumn
    -0.15
    ÑıÑĩ
    -0.14
     Ù¾ÛĮر
    -0.14
    modele
    -0.13
     Arbitrary
    -0.13
     arbitrary
    -0.13
    aturas
    -0.13
    NCY
    -0.13
    POSITIVE LOGITS
    exampleInput
    0.15
     dah
    0.15
    icari
    0.14
     Mend
    0.14
    æ¦
    0.14
    angan
    0.13
    loh
    0.13
    -plugins
    0.13
    éłĥ
    0.12
    303
    0.12
    Activations Density 0.148%

    No Known Activations