© 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. 118662
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation for music and its emotional impact

    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
     relatively
    -0.08
     reasonably
    -0.08
     decent
    -0.07
    æ¯Ķè¾ĥ
    -0.07
     bastante
    -0.07
    éł
    -0.07
    interesting
    -0.07
    è¾ĥ
    -0.07
     nice
    -0.07
    able
    -0.07
    POSITIVE LOGITS
     literally
    0.09
    liter
    0.09
     absolutely
    0.09
     simply
    0.09
     absolute
    0.08
     complete
    0.08
     hoÃłn
    0.07
     Absolutely
    0.07
    Simply
    0.07
    .literal
    0.07
    Activations Density 0.060%

    No Known Activations