© 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. 75036
    Prev
    Next
    INDEX
    Explanations

    references to vehicle performance issues during racing

    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
    vod
    -0.09
    chein
    -0.07
     helicopt
    -0.07
     ecl
    -0.07
    dds
    -0.07
    Äįky
    -0.07
    vertime
    -0.07
     fod
    -0.07
    apol
    -0.07
     ucwords
    -0.07
    POSITIVE LOGITS
     balance
    0.06
     CGRectGet
    0.06
    èİ«
    0.06
     Balance
    0.06
    IBUT
    0.05
    oph
    0.05
     throughout
    0.05
    .req
    0.05
    Balance
    0.05
    QQ
    0.05
    Activations Density 0.005%

    No Known Activations