© 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. 17-LLAMASCOPE-RES-131K
    11. 86897
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with charm and attractiveness

    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
    wards
    -0.08
    eve
    -0.08
    ìĶ
    -0.07
    ye
    -0.07
    dle
    -0.07
    erman
    -0.07
    er
    -0.07
    нÑĸвеÑĢ
    -0.07
    ogle
    -0.07
    .Provider
    -0.06
    POSITIVE LOGITS
    ingly
    0.09
    agne
    0.08
     litt
    0.07
     little
    0.07
    andise
    0.06
    747
    0.06
    sworth
    0.06
    plain
    0.06
    indo
    0.06
    entic
    0.06
    Activations Density 0.006%

    No Known Activations