© 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. 95708
    Prev
    Next
    INDEX
    Explanations

    references to work and professional obligations

    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
    341
    -0.07
    stan
    -0.06
    olar
    -0.06
    avig
    -0.06
    ocal
    -0.06
     Bout
    -0.06
    ordering
    -0.06
    wayne
    -0.06
    erule
    -0.06
     ours
    -0.06
    POSITIVE LOGITS
    /business
    0.08
    solete
    0.07
    帰
    0.07
    γÏĩ
    0.07
    /home
    0.07
    iba
    0.07
    afort
    0.06
    aday
    0.06
    ongan
    0.06
    Pts
    0.06
    Activations Density 0.016%

    No Known Activations