© 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. 9-LLAMASCOPE-RES-131K
    11. 97717
    Prev
    Next
    INDEX
    Explanations

    mentions of tools and equipment related to various trades

    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
    uhan
    -0.08
    iola
    -0.07
    gor
    -0.07
    chio
    -0.07
    ¯
    -0.07
    irá
    -0.07
    infer
    -0.06
    å¹ķ
    -0.06
    ulling
    -0.06
    ierung
    -0.06
    POSITIVE LOGITS
    ç®±
    0.06
    оÑģÑĢед
    0.06
    erson
    0.06
     å·¥
    0.06
     Box
    0.06
    Ac
    0.06
    Nonce
    0.06
    ius
    0.06
    omp
    0.06
    chest
    0.05
    Activations Density 0.010%

    No Known Activations