© 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 EvalsExportsAPI 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. 58899
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to recognition and attribution in the context of music and media

    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
    ourd
    -0.07
    اظ
    -0.07
    elib
    -0.06
    lernen
    -0.06
    ØŃØ«
    -0.06
    ouden
    -0.06
     Hod
    -0.06
     زر
    -0.06
    ALLERY
    -0.06
    createFrom
    -0.06
    POSITIVE LOGITS
     credit
    0.10
     credits
    0.10
     attribution
    0.09
    credits
    0.09
     Credit
    0.08
     créd
    0.08
    credit
    0.07
     attrib
    0.07
     credited
    0.07
     Bott
    0.07
    Activations Density 0.009%

    No Known Activations