© 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 EvalsExportsAPI 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. 56220
    Prev
    Next
    INDEX
    Explanations

    coding related elements and style properties

    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
    teg
    -0.07
    eb
    -0.07
    tgl
    -0.07
    cht
    -0.06
    oleon
    -0.06
    SDL
    -0.06
    bsp
    -0.06
    .Reporting
    -0.06
    awner
    -0.06
     fmt
    -0.06
    POSITIVE LOGITS
     Fell
    0.06
    <decimal
    0.06
     Dive
    0.06
    InChildren
    0.06
    VI
    0.06
     Hack
    0.06
     Casc
    0.06
    ystack
    0.06
     dit
    0.06
    ัà¸ģส
    0.05
    Activations Density 0.001%

    No Known Activations