© 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. 17906
    Prev
    Next
    INDEX
    Explanations

    locations and neighborhoods in relation to services provided

    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
    вÑĸлÑĮ
    -0.08
    оÑĩка
    -0.08
    ĤŃ
    -0.08
    ArgsConstructor
    -0.07
    òng
    -0.07
    ô
    -0.07
    Ú©ÙĪر
    -0.07
    åŃĺäºİ
    -0.07
    ladıģı
    -0.07
     lee
    -0.07
    POSITIVE LOGITS
     guild
    0.06
    near
    0.06
    isman
    0.06
     near
    0.06
    ি
    0.06
    é±
    0.06
    ches
    0.06
    unct
    0.06
     Fleet
    0.06
    xs
    0.05
    Activations Density 0.016%

    No Known Activations