© 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. 80022
    Prev
    Next
    INDEX
    Explanations

    indicators of support, structure, and organization in discussions

    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
    .Driver
    -0.06
    CustomAttributes
    -0.06
    _LR
    -0.06
    ÑĢай
    -0.06
    Debugger
    -0.06
     fitte
    -0.06
    Africa
    -0.06
     incontri
    -0.06
    á»ij
    -0.06
     íķµ
    -0.06
    POSITIVE LOGITS
     USA
    0.07
    eniable
    0.07
    rieving
    0.07
    786
    0.07
    eras
    0.06
    vos
    0.06
    teness
    0.06
    ippi
    0.06
     Android
    0.06
     ApplicationException
    0.06
    Activations Density 0.170%

    No Known Activations