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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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-131K
    6. 78577
    Prev
    Next
    INDEX
    Explanations

    references to the Bible

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rites
    -0.07
    abouts
    -0.07
    ima
    -0.07
    PHY
    -0.07
    naissance
    -0.06
    svn
    -0.06
    us
    -0.06
    755
    -0.06
    nel
    -0.06
    ̣
    -0.06
    POSITIVE LOGITS
    lical
    0.08
    onder
    0.07
    ulumi
    0.07
    Sharper
    0.07
    imple
    0.07
    ÚĨÙĩ
    0.07
    quiv
    0.07
    amarin
    0.07
    Łèĥ½
    0.07
    steder
    0.07
    Activations Density 0.005%

    No Known Activations