© 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. 97714
    Prev
    Next
    INDEX
    Explanations

    references to animal imagery or elements within a narrative context

    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
    -series
    -0.06
    ourd
    -0.06
    ehr
    -0.06
    )prepare
    -0.06
    -sync
    -0.06
    curity
    -0.06
     ÑĢан
    -0.06
    odont
    -0.06
    iese
    -0.06
    opo
    -0.06
    POSITIVE LOGITS
    pector
    0.07
    âĢ¦↵↵↵
    0.07
    extent
    0.07
     blinking
    0.06
    orst
    0.06
    ضاء
    0.06
    928
    0.06
     (č↵
    0.06
    968
    0.06
     Commission
    0.06
    Activations Density 0.001%

    No Known Activations