© 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. 85536
    Prev
    Next
    INDEX
    Explanations

    family-oriented themes and interactions

    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
    isku
    -0.07
    rosso
    -0.07
    crast
    -0.07
    remium
    -0.07
    @"
    -0.07
     дела
    -0.07
    ¡
    -0.06
    avia
    -0.06
    æī§
    -0.06
    xon
    -0.06
    POSITIVE LOGITS
    HeaderValue
    0.07
     demons
    0.07
    illery
    0.06
    Instr
    0.06
     photos
    0.06
    uel
    0.06
    indir
    0.06
     hell
    0.06
    andid
    0.06
     IG
    0.06
    Activations Density 0.021%

    No Known Activations