© 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. 82919
    Prev
    Next
    INDEX
    Explanations

    references to news articles and media sources

    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
    olk
    -0.07
    "><!--
    -0.07
    byn
    -0.06
    :async
    -0.06
    emez
    -0.06
    ammad
    -0.06
    oine
    -0.06
    pll
    -0.06
     УкÑĢаÑĹ
    -0.06
    elow
    -0.06
    POSITIVE LOGITS
     Times
    0.11
     newspaper
    0.10
     Daily
    0.10
    Times
    0.10
     newspapers
    0.10
    Daily
    0.09
     Herald
    0.09
     Courier
    0.09
    quirer
    0.09
     Tribune
    0.09
    Activations Density 0.245%

    No Known Activations