© 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. 106867
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or sarcasm in conversational contexts

    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
    alley
    -0.07
    .mj
    -0.06
    RefPtr
    -0.06
    aware
    -0.06
    еÑģÑĤи
    -0.06
    TTY
    -0.06
    argas
    -0.06
    便
    -0.06
    aley
    -0.06
    ï¿
    -0.06
    POSITIVE LOGITS
     hafta
    0.08
    forum
    0.07
    morph
    0.07
    fen
    0.07
     '
    0.06
    è¾°
    0.06
     Moderator
    0.06
     chicas
    0.06
    eken
    0.06
     temp
    0.06
    Activations Density 0.044%

    No Known Activations