© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40746
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical appearance and performance in contexts of entertainment or media

    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
     âľĵ
    -0.07
    steder
    -0.07
     Anonymous
    -0.07
    logan
    -0.07
    ernel
    -0.07
    ź
    -0.07
    _BEGIN
    -0.06
     permanent
    -0.06
    lect
    -0.06
    pong
    -0.06
    POSITIVE LOGITS
     Instagram
    0.07
     BTS
    0.06
    »¿
    0.06
     fans
    0.06
     Cand
    0.06
     followers
    0.06
     editorial
    0.06
     candid
    0.06
     shots
    0.06
    iges
    0.06
    Activations Density 0.005%

    No Known Activations