© 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. 17-LLAMASCOPE-RES-131K
    11. 41521
    Prev
    Next
    INDEX
    Explanations

    expressions related to listening and hearing

    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
    uji
    -0.07
    orpor
    -0.07
    /cop
    -0.07
    orz
    -0.07
    ugins
    -0.07
    echa
    -0.07
    uries
    -0.07
    MENT
    -0.07
    598
    -0.07
    /YYYY
    -0.07
    POSITIVE LOGITS
     about
    0.07
     explanation
    0.07
     how
    0.06
     testimony
    0.06
     case
    0.06
    itan
    0.06
     directly
    0.06
     explanations
    0.06
     stories
    0.06
    iant
    0.06
    Activations Density 0.010%

    No Known Activations