© 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. 15-LLAMASCOPE-RES-131K
    11. 61539
    Prev
    Next
    INDEX
    Explanations

    descriptors of physical appearance

    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
    оÑĢаз
    -0.08
     anale
    -0.07
    pendicular
    -0.07
     unborn
    -0.06
    à¸Ńà¸ŀ
    -0.06
    egin
    -0.06
    Ïĥμο
    -0.06
    æ°
    -0.06
    iks
    -0.06
     Episodes
    -0.06
    POSITIVE LOGITS
     facial
    0.09
     appearance
    0.08
     beauty
    0.07
     look
    0.07
     aging
    0.07
     face
    0.07
     Facial
    0.07
    Beauty
    0.07
     frontal
    0.07
    Appear
    0.07
    Activations Density 0.121%

    No Known Activations