© 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. 92335
    Prev
    Next
    INDEX
    Explanations

    elements related to legal qualifications and affiliations

    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
    abin
    -0.07
    esta
    -0.07
    iera
    -0.07
     ÐļÑĢаÑĹна
    -0.07
    ieri
    -0.07
    olet
    -0.06
    zar
    -0.06
    inkle
    -0.06
    olina
    -0.06
    iment
    -0.06
    POSITIVE LOGITS
     Certificate
    0.07
    æĵ
    0.07
    ;"><?
    0.06
     Recreation
    0.06
    kop
    0.06
    iples
    0.06
     Languages
    0.06
    urv
    0.06
     yp
    0.06
     recipient
    0.06
    Activations Density 0.031%

    No Known Activations