© 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. 124630
    Prev
    Next
    INDEX
    Explanations

    comments and annotations in code documentation

    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
    .$.
    -0.07
    ramer
    -0.07
    opi
    -0.07
    ullet
    -0.07
     lit
    -0.06
    ̧
    -0.06
    enschaft
    -0.06
     hl
    -0.06
    nze
    -0.06
    isten
    -0.06
    POSITIVE LOGITS
    .bunifuFlatButton
    0.07
    kate
    0.06
    ç·
    0.06
     Kerr
    0.06
     Aerospace
    0.06
    èĮĤ
    0.06
    CHAT
    0.06
     femin
    0.06
     astore
    0.06
    untu
    0.05
    Activations Density 0.015%

    No Known Activations