© 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. 69880
    Prev
    Next
    INDEX
    Explanations

    references to refreshing or updating processes

    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
    gie
    -0.07
    tie
    -0.07
    anza
    -0.07
    коÑĤ
    -0.07
    lify
    -0.07
    shiv
    -0.06
    unu
    -0.06
    ÏĦεÏģα
    -0.06
    жив
    -0.06
    jee
    -0.06
    POSITIVE LOGITS
    ingly
    0.12
    ments
    0.11
    ment
    0.10
    es
    0.10
    /update
    0.09
    ers
    0.08
    able
    0.08
    (es
    0.07
    eting
    0.07
    /rest
    0.07
    Activations Density 0.004%

    No Known Activations