© 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. 91962
    Prev
    Next
    INDEX
    Explanations

    references to government policies and decisions

    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
    rieg
    -0.07
    iko
    -0.07
     Fund
    -0.06
     Chaos
    -0.06
     chaos
    -0.06
     m
    -0.05
     jwt
    -0.05
     St
    -0.05
     excess
    -0.05
    kır
    -0.05
    POSITIVE LOGITS
    abei
    0.10
    piler
    0.08
    ompiler
    0.07
    ubar
    0.07
    iddleware
    0.07
    ofile
    0.07
    ìļ°
    0.07
    ÑĢÑĥн
    0.07
    ainment
    0.07
    bilder
    0.07
    Activations Density 0.000%

    No Known Activations