© 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. 86593
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific occurrences and actions taken

    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
    anzeigen
    -0.07
    awe
    -0.07
    auen
    -0.07
    alama
    -0.07
    olumn
    -0.07
    fullscreen
    -0.07
    celik
    -0.06
    others
    -0.06
    bao
    -0.06
    -spacing
    -0.06
    POSITIVE LOGITS
     ration
    0.06
    ÃĸL
    0.06
    ì²´
    0.06
    274
    0.06
     entirely
    0.06
     genuine
    0.06
    686
    0.06
    recision
    0.06
    dana
    0.06
     units
    0.06
    Activations Density 0.077%

    No Known Activations