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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5331
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic expression and creativity

    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
    iche
    -0.07
    ut
    -0.06
    ,[],
    -0.06
    nad
    -0.06
    obody
    -0.06
     Nobody
    -0.06
     mee
    -0.06
     boiler
    -0.05
    ica
    -0.05
    emp
    -0.05
    POSITIVE LOGITS
     noticing
    0.11
     beauty
    0.10
    Beauty
    0.09
    eÅŁ
    0.08
     Beauty
    0.08
     observation
    0.08
    noticed
    0.08
     notice
    0.08
     noticed
    0.08
     observations
    0.08
    Activations Density 0.042%

    No Known Activations