© 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. 94019
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and acknowledgment in communication

    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
    737
    -0.06
    \CMS
    -0.06
     Furn
    -0.05
     Stevens
    -0.05
    udeau
    -0.05
    tics
    -0.05
    istream
    -0.05
     fir
    -0.05
    ander
    -0.05
    istics
    -0.05
    POSITIVE LOGITS
     comment
    0.08
     comentario
    0.08
    comment
    0.07
     comments
    0.07
     Dent
    0.07
     feedback
    0.07
    comments
    0.07
    .flink
    0.07
    irim
    0.07
     COMMENTS
    0.07
    Activations Density 0.005%

    No Known Activations