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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 60824
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure elements in a document

    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
    zell
    -0.07
    IDA
    -0.06
     Registrar
    -0.06
    ané
    -0.06
    aron
    -0.06
    achuset
    -0.06
    isoft
    -0.06
    malink
    -0.06
    دة
    -0.06
    gger
    -0.06
    POSITIVE LOGITS
    ivor
    0.07
    obe
    0.07
    divid
    0.07
    lat
    0.07
    div
    0.07
     Hutchinson
    0.07
    til
    0.07
    nings
    0.06
     til
    0.06
    borg
    0.06
    Activations Density 0.019%

    No Known Activations