© 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. 29410
    Prev
    Next
    INDEX
    Explanations

    labels or section markers in the text

    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
    abase
    -0.07
    ì¶ľ
    -0.07
    anno
    -0.07
    czy
    -0.06
     loading
    -0.06
    ponents
    -0.06
     Merchant
    -0.06
    út
    -0.06
    bum
    -0.06
     Vas
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    jac
    0.07
    .eof
    0.07
     INTERRUPTION
    0.06
    odzi
    0.06
    ONES
    0.06
    olated
    0.06
    ëĿ½
    0.06
    Ports
    0.06
    xon
    0.06
    Activations Density 0.013%

    No Known Activations