© 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 EvalsExportsAPI 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. 78456
    Prev
    Next
    INDEX
    Explanations

    words signifying emphasis or frequency

    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
    refs
    -0.08
    /loose
    -0.07
    á»IJ
    -0.07
    ãĥŃãĥ¼
    -0.07
    campo
    -0.07
    ÂŃi
    -0.07
    Òij
    -0.07
    TY
    -0.07
     otel
    -0.07
     pii
    -0.07
    POSITIVE LOGITS
     the
    0.07
     what
    0.07
     that
    0.06
    ürk
    0.06
    mir
    0.06
    isto
    0.06
     succ
    0.06
    ewhat
    0.06
    æľºåħ³
    0.06
    ÙĨز
    0.06
    Activations Density 0.075%

    No Known Activations