© 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. 73423
    Prev
    Next
    INDEX
    Explanations

    inquiries about people's identities and occupations

    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
    anch
    -0.06
     bund
    -0.06
     ener
    -0.06
    ..
    -0.06
     sequel
    -0.06
    543
    -0.05
     IMapper
    -0.05
    bih
    -0.05
    amazon
    -0.05
     Strauss
    -0.05
    POSITIVE LOGITS
    _exports
    0.07
    .heroku
    0.07
    uilder
    0.07
    HWND
    0.07
    FRING
    0.07
     Clinic
    0.07
    .opensource
    0.07
    شتÙĩ
    0.07
    onical
    0.07
    .finished
    0.07
    Activations Density 0.008%

    No Known Activations