© 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. 58495
    Prev
    Next
    INDEX
    Explanations

    references to specific districts

    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
    ÑĮми
    -0.08
    ufen
    -0.07
    аÑĢÑĮ
    -0.07
    OrUpdate
    -0.07
    lings
    -0.07
    opard
    -0.07
    essler
    -0.07
    pty
    -0.07
     whim
    -0.07
    ếp
    -0.07
    POSITIVE LOGITS
    wide
    0.13
    -wide
    0.12
    /Area
    0.10
    -Level
    0.10
    -level
    0.09
    /state
    0.09
    edImage
    0.08
    Wide
    0.08
    naire
    0.08
    son
    0.07
    Activations Density 0.016%

    No Known Activations