Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44308
    Prev
    Next
    INDEX
    Explanations

    expressions related to artistic techniques and color application in painting

    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
    icha
    -0.09
    DisplayStyle
    -0.07
     Brewing
    -0.07
     Axes
    -0.06
     ROUT
    -0.06
    eln
    -0.06
    ól
    -0.06
    ebi
    -0.06
    éĥ¨å±ĭ
    -0.06
     身
    -0.06
    POSITIVE LOGITS
     values
    0.09
     Values
    0.09
     value
    0.09
     alla
    0.09
     passages
    0.08
     wet
    0.08
     wash
    0.08
     gl
    0.08
     transparent
    0.08
     sf
    0.08
    Activations Density 0.020%

    No Known Activations