© 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. 105428
    Prev
    Next
    INDEX
    Explanations

    terms related to innovation

    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
    laden
    -0.08
    zelf
    -0.07
     Cres
    -0.07
    UNK
    -0.07
    anas
    -0.07
    UTH
    -0.07
    untas
    -0.07
    eo
    -0.07
    IFF
    -0.07
    gings
    -0.07
    POSITIVE LOGITS
    s
    0.09
    ations
    0.08
    ative
    0.08
    est
    0.07
    739
    0.07
    /npm
    0.07
    ات
    0.07
    removeAttr
    0.07
    enga
    0.07
    aki
    0.07
    Activations Density 0.003%

    No Known Activations