© 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. 86457
    Prev
    Next
    INDEX
    Explanations

    references to authors and scientific publications

    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
    èį·
    -0.07
    ainties
    -0.07
    icari
    -0.07
    orget
    -0.06
    reten
    -0.06
    quier
    -0.06
    _CMP
    -0.06
     Cancer
    -0.06
     Skeleton
    -0.06
    clidean
    -0.06
    POSITIVE LOGITS
     Infect
    0.10
     infectious
    0.10
     vir
    0.08
     infect
    0.08
     vi
    0.08
     Surveillance
    0.08
     surveillance
    0.08
     Epidemi
    0.07
     ви
    0.07
     bacterial
    0.07
    Activations Density 0.130%

    No Known Activations