© 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. 72718
    Prev
    Next
    INDEX
    Explanations

    references to composers and their works

    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
    orrent
    -0.07
    OfMonth
    -0.07
    imax
    -0.07
    quet
    -0.06
    oca
    -0.06
    Accessor
    -0.06
    apid
    -0.06
    ÏĮÏĤ
    -0.06
    AF
    -0.06
    quets
    -0.06
    POSITIVE LOGITS
    commission
    0.07
     piece
    0.07
    onal
    0.07
     commissioned
    0.07
     recom
    0.07
     superf
    0.07
     commission
    0.06
     chamber
    0.06
     fl
    0.06
     bour
    0.06
    Activations Density 0.028%

    No Known Activations