© 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. 80278
    Prev
    Next
    INDEX
    Explanations

    numerical data and references in technical 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
    oeff
    -0.06
    rado
    -0.06
    i
    -0.06
    óm
    -0.06
    hi
    -0.06
     âĢ¦
    -0.06
     Andrew
    -0.05
     Dynasty
    -0.05
    -0.05
    zek
    -0.05
    POSITIVE LOGITS
    íĨ¡
    0.07
    ÐĶÐļ
    0.07
    croft
    0.07
    ãĥ¥ãĥ¼
    0.07
    GuidId
    0.07
     OTHERWISE
    0.07
    plates
    0.07
    -INF
    0.07
    -lfs
    0.07
    ůst
    0.07
    Activations Density 0.007%

    No Known Activations