© 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. 40426
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or addresses

    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
    itu
    -0.06
    acob
    -0.06
    azzi
    -0.06
    lsru
    -0.06
     Singer
    -0.06
     Äijạo
    -0.06
    ensburg
    -0.06
    utzer
    -0.06
    riday
    -0.06
    ÑĢо
    -0.06
    POSITIVE LOGITS
    ManagedObjectContext
    0.08
     "('
    0.07
    (LP
    0.06
    (Arg
    0.06
    esto
    0.06
    AffineTransform
    0.06
     Morrow
    0.06
    andi
    0.06
    -scrollbar
    0.06
     Dudley
    0.06
    Activations Density 0.000%

    No Known Activations