© 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. 57312
    Prev
    Next
    INDEX
    Explanations

    references to objects or components in technical descriptions

    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
    ırak
    -0.08
     ÑģмеÑĪ
    -0.08
    nnen
    -0.08
    .MixedReality
    -0.08
    ecko
    -0.08
    errick
    -0.08
    .GroupLayout
    -0.07
     ?><
    -0.07
    ække
    -0.07
    ?><
    -0.07
    POSITIVE LOGITS
     many
    0.08
     some
    0.07
     our
    0.07
     most
    0.07
     otherwise
    0.06
    older
    0.06
     countless
    0.06
    ika
    0.05
    elta
    0.05
    WA
    0.05
    Activations Density 0.023%

    No Known Activations