© 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. 74427
    Prev
    Next
    INDEX
    Explanations

    references to music, performance, and entertainment-related concepts

    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
     beden
    -0.08
    над
    -0.08
    ignet
    -0.07
    ï¼Ĵï¼IJ
    -0.07
    iffe
    -0.07
    åŃĿ
    -0.07
     ErrorResponse
    -0.07
    .IsNullOr
    -0.07
     iddi
    -0.07
    /interface
    -0.07
    POSITIVE LOGITS
     et
    0.06
     Randall
    0.06
     fill
    0.06
     over
    0.06
     randomly
    0.05
    Unnamed
    0.05
    elas
    0.05
    163
    0.05
     and
    0.05
     filled
    0.05
    Activations Density 0.036%

    No Known Activations