© 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. 104716
    Prev
    Next
    INDEX
    Explanations

    references to musical equipment and setups

    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
    Dash
    -0.07
    _dash
    -0.07
     Dash
    -0.07
    resher
    -0.07
     executive
    -0.07
     cad
    -0.07
    εκ
    -0.07
    ãĥ©ãĤ¯
    -0.07
    /exec
    -0.07
    odo
    -0.06
    POSITIVE LOGITS
     guitars
    0.08
     guitar
    0.08
     distortion
    0.08
    stage
    0.07
     Stage
    0.07
     Feedback
    0.07
     Guitar
    0.07
    Feedback
    0.06
     guit
    0.06
    ernaut
    0.06
    Activations Density 0.009%

    No Known Activations