© 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. 17-LLAMASCOPE-RES-32K
    6. 15314
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alc
    -0.19
    alous
    -0.18
    alo
    -0.16
     Heller
    -0.16
    504
    -0.15
    ecer
    -0.15
    alic
    -0.15
    alarm
    -0.15
    SearchParams
    -0.14
    indsight
    -0.14
    POSITIVE LOGITS
    nable
    0.18
     каÑĢÑĤи
    0.15
    -LAST
    0.14
    à¤Ĥà¤ĺ
    0.14
     Hayward
    0.14
     Bibli
    0.14
    à¤Ĥध
    0.14
    ìķ¼
    0.14
    BUF
    0.14
     Continent
    0.14
    Activations Density 0.026%

    No Known Activations