© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94527
    Prev
    Next
    INDEX
    Explanations

    financial or monetary values

    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
    Ïģί
    -0.08
    _stdio
    -0.07
    utherford
    -0.07
    abcdefghijkl
    -0.07
    ?key
    -0.07
    abcdefghijklmnop
    -0.07
    alytics
    -0.07
    оÑĤи
    -0.07
    ResponseStatus
    -0.07
    .rf
    -0.07
    POSITIVE LOGITS
    /or
    0.14
    quot
    0.11
     alike
    0.10
    rog
    0.08
    orra
    0.07
    rag
    0.07
    /OR
    0.07
    rogen
    0.07
    наÑĩе
    0.07
    raquo
    0.07
    Activations Density 0.042%

    No Known Activations