© 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. 5470
    Prev
    Next
    INDEX
    Explanations

    references to achievements and successes in competitive contexts

    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
    esteem
    -0.07
    ?key
    -0.07
    à¸Ľà¸£à¸°à¸ģ
    -0.07
    PÅĻed
    -0.07
    achel
    -0.07
    åĿĬ
    -0.07
    .Solid
    -0.07
     åIJ
    -0.07
    getService
    -0.07
    ixel
    -0.07
    POSITIVE LOGITS
     stable
    0.08
     horses
    0.07
     fec
    0.06
     entries
    0.06
     Dual
    0.06
     dual
    0.06
    entries
    0.06
     j
    0.06
     Entries
    0.06
     Stable
    0.06
    Activations Density 0.004%

    No Known Activations