© 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. 88885
    Prev
    Next
    INDEX
    Explanations

    formal disclaimers and conditions

    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
     sometimes
    -0.06
     if
    -0.06
    tron
    -0.06
    erk
    -0.05
    i
    -0.05
    hill
    -0.05
    088
    -0.05
     dot
    -0.05
    isset
    -0.05
    some
    -0.05
    POSITIVE LOGITS
    ORIA
    0.08
    ODO
    0.08
    _HINT
    0.08
    reesome
    0.07
    cente
    0.07
    _DISPATCH
    0.07
    ",__
    0.07
    odem
    0.07
    okino
    0.07
    #End
    0.07
    Activations Density 0.003%

    No Known Activations