© 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. 108300
    Prev
    Next
    INDEX
    Explanations

    HTML attributes in a structured format

    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
    fu
    -0.06
    lops
    -0.06
    otta
    -0.06
    loon
    -0.06
    andy
    -0.06
    igon
    -0.06
     genu
    -0.06
    nine
    -0.05
    322
    -0.05
    u
    -0.05
    POSITIVE LOGITS
     доÑĤ
    0.08
    inea
    0.08
    #ad
    0.07
     tato
    0.07
     addCriterion
    0.07
    #ab
    0.07
    ¢åįķ
    0.07
    à¥įबर
    0.07
    ÎĪ
    0.07
    .ra
    0.07
    Activations Density 0.002%

    No Known Activations