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

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125458
    Prev
    Next
    INDEX
    Explanations

    references to government services and affairs

    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
    zyst
    -0.06
    oad
    -0.06
    anny
    -0.06
    ongan
    -0.06
    hk
    -0.06
     Factor
    -0.06
     diss
    -0.06
     Fav
    -0.06
     factor
    -0.06
    -factor
    -0.05
    POSITIVE LOGITS
    á»ĥn
    0.08
    aeda
    0.07
    ains
    0.07
    물ìĿĦ
    0.06
    ión
    0.06
    asley
    0.06
    using
    0.06
    ách
    0.06
    .digital
    0.06
    otton
    0.06
    Activations Density 0.000%

    No Known Activations