© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125462
    Prev
    Next
    INDEX
    Explanations

    programming code segments and syntax

    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
     Weinstein
    -0.07
    geois
    -0.06
    .mu
    -0.06
    /browse
    -0.06
    ICA
    -0.06
    pton
    -0.06
    ica
    -0.06
    UnitOfWork
    -0.06
     Baldwin
    -0.06
    anou
    -0.06
    POSITIVE LOGITS
    PEED
    0.07
    APER
    0.07
     logic
    0.06
    IDD
    0.06
     Alphabet
    0.06
    poser
    0.06
     ADDRESS
    0.06
    WithOptions
    0.06
    aper
    0.06
    phabet
    0.06
    Activations Density 0.000%

    No Known Activations