Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 13-LLAMASCOPE-RES-32K
    6. 19005
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .decor
    -0.16
    кÑģ
    -0.15
    reater
    -0.15
    uada
    -0.15
    ollo
    -0.15
    STANCE
    -0.14
    Pragma
    -0.14
    rias
    -0.14
    Ñħодим
    -0.14
    ÅĽci
    -0.14
    POSITIVE LOGITS
    ³
    0.15
    wort
    0.14
    utut
    0.14
    Sz
    0.14
     bron
    0.14
    ÐĴÐIJ
    0.13
    inke
    0.13
    ziel
    0.13
    lauf
    0.13
     influ
    0.13
    Activations Density 0.004%

    No Known Activations