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. 43969
    Prev
    Next
    INDEX
    Explanations

    discussions about creativity and the artistic process

    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
    ilver
    -0.06
    νÏİ
    -0.05
    wap
    -0.05
    _locals
    -0.05
    رخ
    -0.05
     Interracial
    -0.05
    ÑģÑĤÑĸ
    -0.05
     WARRANT
    -0.05
    ylko
    -0.05
    levation
    -0.05
    POSITIVE LOGITS
     artists
    0.22
     Artists
    0.22
     artist
    0.21
     artistic
    0.21
     Artist
    0.20
     art
    0.19
    artist
    0.19
    Artist
    0.19
    artists
    0.18
     Art
    0.17
    Activations Density 0.068%

    No Known Activations