© 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. 2-LLAMASCOPE-RES-32K
    6. 4360
    Prev
    Next
    INDEX
    Explanations

    instances of high numerical values representing importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ctl
    -0.17
    illon
    -0.16
    pard
    -0.16
     milano
    -0.15
    ãĤº
    -0.15
    efa
    -0.15
    auf
    -0.14
    ÑĢел
    -0.14
    .codehaus
    -0.14
    cret
    -0.14
    POSITIVE LOGITS
    akan
    0.18
     ìĤ¬íķŃ
    0.17
    aste
    0.16
    å¾
    0.14
    ASTE
    0.14
       
    0.14
    /Area
    0.14
    uben
    0.14
     Vaugh
    0.14
    Advisor
    0.13
    Activations Density 0.051%

    No Known Activations