© 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. 106671
    Prev
    Next
    INDEX
    Explanations

    questions that begin with "when."

    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
    artment
    -0.07
    tte
    -0.07
    azzi
    -0.07
    ulls
    -0.07
    geh
    -0.06
    isser
    -0.06
    .fhir
    -0.06
    ummings
    -0.06
    .getChildAt
    -0.06
     åĬł
    -0.06
    POSITIVE LOGITS
    ubo
    0.08
     did
    0.08
     Micha
    0.07
    did
    0.07
    EVER
    0.07
    νι
    0.07
     does
    0.06
    .did
    0.06
    AttributeName
    0.06
    verbosity
    0.06
    Activations Density 0.011%

    No Known Activations