© 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. 61972
    Prev
    Next
    INDEX
    Explanations

    numerical values with high significance or relevance

    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
    iggins
    -0.08
     Incontri
    -0.08
    éĴŁ
    -0.07
    дина
    -0.07
    getSingleton
    -0.07
    /activity
    -0.07
    zcze
    -0.07
     rencont
    -0.07
    дÑı
    -0.07
    PÅĻed
    -0.07
    POSITIVE LOGITS
    ran
    0.07
    bum
    0.06
    ali
    0.06
    cul
    0.06
     Lad
    0.06
    ä»ĭ
    0.06
     short
    0.05
    ug
    0.05
     resc
    0.05
     formal
    0.05
    Activations Density 0.011%

    No Known Activations