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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 42339
    Prev
    Next
    INDEX
    Explanations

    references to various forms of aid and assistance programs

    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
    ross
    -0.07
    umbling
    -0.07
    ugg
    -0.06
    ìŀ¡
    -0.06
    emed
    -0.06
     Peb
    -0.06
    uplicates
    -0.06
    (s
    -0.06
     endoth
    -0.06
    weit
    -0.06
    POSITIVE LOGITS
    ë°Ľ
    0.07
    .components
    0.07
    ÏĥÏħ
    0.07
     Coord
    0.07
    _OCCURRED
    0.07
    ÙĤØ·
    0.07
    inton
    0.07
    iciar
    0.06
    .bio
    0.06
    hani
    0.06
    Activations Density 0.009%

    No Known Activations