© 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. 129090
    Prev
    Next
    INDEX
    Explanations

    details related to social gatherings and personal 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
     Sür
    -0.06
     Implementation
    -0.06
     unpopular
    -0.06
     Realty
    -0.05
    fst
    -0.05
     Geme
    -0.05
    Implementation
    -0.05
    gest
    -0.05
    çĽijçĿ£
    -0.05
     suffix
    -0.05
    POSITIVE LOGITS
     dress
    0.12
     Dress
    0.11
     dressing
    0.10
     dressed
    0.10
    dress
    0.09
     appearance
    0.09
     dresses
    0.09
     Appearance
    0.08
     outfit
    0.08
    undy
    0.07
    Activations Density 0.053%

    No Known Activations