© 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. 18072
    Prev
    Next
    INDEX
    Explanations

    references to online platforms and content interaction

    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
    rame
    -0.07
    affer
    -0.06
     Chamber
    -0.06
    rais
    -0.06
     Deg
    -0.06
    aiser
    -0.06
    obe
    -0.06
    ponder
    -0.06
     Cure
    -0.06
     excess
    -0.06
    POSITIVE LOGITS
    //------------------------------------------------------------------------------↵↵
    0.07
    éĽĦ
    0.06
    TOTYPE
    0.06
     nack
    0.06
    omen
    0.06
     Ukra
    0.06
    VERTISE
    0.06
    ventions
    0.06
    ActivityIndicator
    0.06
    ullo
    0.06
    Activations Density 0.003%

    No Known Activations