© 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. 92281
    Prev
    Next
    INDEX
    Explanations

    accomplishments and recognition in music

    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
     drummer
    -0.09
     Drum
    -0.08
    اشت
    -0.07
     Ballet
    -0.07
    aurant
    -0.07
    iband
    -0.07
     danced
    -0.07
    ıf
    -0.07
    opp
    -0.07
    agem
    -0.07
    POSITIVE LOGITS
     singing
    0.10
     voice
    0.10
     sing
    0.09
     vocal
    0.09
     Voice
    0.09
     oper
    0.08
     cro
    0.08
     Sing
    0.08
     sopr
    0.07
     sings
    0.07
    Activations Density 0.291%

    No Known Activations