© 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. 86393
    Prev
    Next
    INDEX
    Explanations

    references to visual content formats such as essays, infographics, and reviews

    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
    /dom
    -0.07
    @mail
    -0.06
    -mean
    -0.06
    éĩ
    -0.06
    err
    -0.06
    Äįen
    -0.06
     sát
    -0.06
    лоп
    -0.05
    _PF
    -0.05
     (:
    -0.05
    POSITIVE LOGITS
    :
    0.15
    ा:
    0.09
    ibold
    0.09
    ieber
    0.08
    ï¼ļ
    0.07
    orelease
    0.07
    orz
    0.07
    ivery
    0.07
    ectl
    0.07
     alert
    0.07
    Activations Density 0.035%

    No Known Activations