© 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. 82860
    Prev
    Next
    INDEX
    Explanations

    definite articles and demonstrative pronouns

    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
    ly
    -0.08
    avis
    -0.07
    -
    -0.06
    iyah
    -0.06
     Wash
    -0.06
    343
    -0.06
    871
    -0.06
    see
    -0.06
    iy
    -0.06
    utter
    -0.06
    POSITIVE LOGITS
    oping
    0.09
    .gdx
    0.07
    engin
    0.07
     latter
    0.07
    лож
    0.07
    fld
    0.07
    fromJson
    0.07
    óm
    0.07
    ureau
    0.07
    ppe
    0.07
    Activations Density 0.003%

    No Known Activations