© 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. 9-LLAMASCOPE-RES-131K
    11. 94431
    Prev
    Next
    INDEX
    Explanations

    references to specific formats and metadata in documents

    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
    leta
    -0.06
    ure
    -0.06
    iddy
    -0.06
     pearls
    -0.06
    gart
    -0.06
    arious
    -0.05
    aña
    -0.05
     Schneider
    -0.05
    ording
    -0.05
     Morrison
    -0.05
    POSITIVE LOGITS
    azon
    0.08
     incent
    0.08
    iminal
    0.08
    prak
    0.07
    nicos
    0.07
    imson
    0.07
    оÑĢони
    0.07
     kancel
    0.06
    åįļ
    0.06
    丸
    0.06
    Activations Density 0.000%

    No Known Activations