© 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 EvalsExportsAPI 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. 86105
    Prev
    Next
    INDEX
    Explanations

    content related to ongoing events or updates

    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
    .editor
    -0.07
    VERTISE
    -0.07
    áž
    -0.07
    olen
    -0.07
    ponde
    -0.07
     تÙĤÙĪ
    -0.07
    ayi
    -0.06
    ffen
    -0.06
    ubern
    -0.06
    ÅĽcie
    -0.06
    POSITIVE LOGITS
     repeated
    0.11
     repeat
    0.10
     repeatedly
    0.10
     regularly
    0.10
     Repeat
    0.10
    Repeat
    0.09
    repeat
    0.09
     bookmark
    0.09
     revisit
    0.09
     frequent
    0.09
    Activations Density 0.036%

    No Known Activations