© 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. 56211
    Prev
    Next
    INDEX
    Explanations

    references to a database library or framework

    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
    avanaugh
    -0.08
    addock
    -0.07
    ampler
    -0.07
    cala
    -0.07
    ilm
    -0.07
    ining
    -0.07
    acad
    -0.07
    NotNull
    -0.07
    ted
    -0.07
    things
    -0.07
    POSITIVE LOGITS
    ment
    0.07
    esz
    0.07
    strap
    0.07
    ified
    0.07
    gli
    0.06
    burgh
    0.06
    forth
    0.06
    pit
    0.06
    back
    0.06
    .rc
    0.06
    Activations Density 0.000%

    No Known Activations