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. 22-LLAMASCOPE-RES-131K
    6. 5615
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical appearance, particularly focusing on facial features

    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
    inan
    -0.07
    anke
    -0.06
    azole
    -0.06
    nee
    -0.06
    izard
    -0.06
    WSC
    -0.06
    nees
    -0.06
    ãģ£ãģ±
    -0.06
     Gerard
    -0.06
    fifo
    -0.06
    POSITIVE LOGITS
     brows
    0.19
     eyebrows
    0.17
     brow
    0.17
     Brow
    0.17
     eyebrow
    0.17
    çľī
    0.14
     Ey
    0.13
    Ey
    0.12
     eyel
    0.12
    ey
    0.10
    Activations Density 0.020%

    No Known Activations