© 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. 29241
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript code snippets

    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
     Colombian
    -0.07
    DCF
    -0.07
    207
    -0.06
    siyon
    -0.06
    elas
    -0.06
     Columbia
    -0.06
    맥
    -0.06
     Colombia
    -0.06
    psc
    -0.06
    å¿
    -0.06
    POSITIVE LOGITS
     Illinois
    0.09
     Missouri
    0.08
     Kansas
    0.08
    Kansas
    0.07
    imestone
    0.07
     Prairie
    0.07
     Iowa
    0.07
    (æĹ¥
    0.07
    à¹Ĥม
    0.07
    ili
    0.07
    Activations Density 0.009%

    No Known Activations