© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 96439
    Prev
    Next
    INDEX
    Explanations

    specific terms related to artistic and creative expressions

    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
    à¥Ĥब
    -0.07
    apiro
    -0.07
    gil
    -0.07
    nie
    -0.06
    plex
    -0.06
    awei
    -0.06
    conj
    -0.06
     BÃŃ
    -0.06
    gie
    -0.06
    asha
    -0.06
    POSITIVE LOGITS
     Syn
    0.07
    -esque
    0.06
    aginator
    0.06
    ypad
    0.06
    -style
    0.06
    -like
    0.06
     style
    0.06
    ısından
    0.06
    -type
    0.06
     type
    0.06
    Activations Density 0.062%

    No Known Activations