© 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. 30057
    Prev
    Next
    INDEX
    Explanations

    numerical references or structured metadata in the text

    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
    çļĦäºĭ
    -0.07
    rieben
    -0.06
    ÑĢовеÑĢ
    -0.06
    etak
    -0.06
    trinsic
    -0.06
    rix
    -0.06
    ilan
    -0.06
    ritable
    -0.06
     Constitution
    -0.06
    inate
    -0.06
    POSITIVE LOGITS
    zon
    0.08
    yon
    0.06
    лика
    0.06
    jon
    0.06
    enu
    0.06
     Aid
    0.06
    upa
    0.06
     Isl
    0.06
    вÑĢоп
    0.06
    KeyValue
    0.06
    Activations Density 0.001%

    No Known Activations