© 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. 15-LLAMASCOPE-RES-131K
    11. 86548
    Prev
    Next
    INDEX
    Explanations

    expressions of resolve or determination

    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
    vez
    -0.11
    ylum
    -0.06
    _PIXEL
    -0.06
    ritten
    -0.06
     каÑģ
    -0.06
    roken
    -0.06
    æĿŁ
    -0.06
    pire
    -0.06
    essages
    -0.06
    _ASSUME
    -0.06
    POSITIVE LOGITS
    ness
    0.09
    ly
    0.08
    /request
    0.08
    ahir
    0.08
     OPTIONAL
    0.07
     Král
    0.07
    NESS
    0.07
    ance
    0.07
    ergarten
    0.06
     pursuit
    0.06
    Activations Density 0.006%

    No Known Activations