© 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. 124719
    Prev
    Next
    INDEX
    Explanations

    statements of consequence or notable events

    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
    zing
    -0.07
    cribe
    -0.07
    ardon
    -0.07
    Expires
    -0.06
     mistake
    -0.06
    ories
    -0.06
    Ç
    -0.06
    asser
    -0.06
     æ°¸
    -0.06
     mourn
    -0.05
    POSITIVE LOGITS
    ære
    0.07
    llib
    0.07
    ÑĤаж
    0.07
    amedi
    0.07
    ucch
    0.07
    coes
    0.07
    pressed
    0.06
     ustanov
    0.06
    Pressed
    0.06
    celik
    0.06
    Activations Density 0.012%

    No Known Activations