© 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. 120422
    Prev
    Next
    INDEX
    Explanations

    occurrences of code syntax or programming structure

    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
    ingo
    -0.06
    ilar
    -0.06
     imp
    -0.06
     Tobacco
    -0.06
    reland
    -0.06
     Lips
    -0.06
    inois
    -0.06
    _SCL
    -0.06
    insk
    -0.06
    okin
    -0.06
    POSITIVE LOGITS
    ynchronously
    0.08
    IGGER
    0.07
    AUSE
    0.07
    olumn
    0.06
    еÑĢеж
    0.06
     bì
    0.06
    uz
    0.06
    ÑĭÑħ
    0.06
    CLUDED
    0.06
    CLA
    0.06
    Activations Density 0.000%

    No Known Activations