© 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. 125384
    Prev
    Next
    INDEX
    Explanations

    instances of gratitude and acknowledgment

    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
     area
    -0.06
    Area
    -0.06
     spokesman
    -0.06
     Wheat
    -0.06
     Area
    -0.06
     proh
    -0.06
     guy
    -0.06
     Ill
    -0.06
    417
    -0.06
     ethnicity
    -0.06
    POSITIVE LOGITS
    alars
    0.08
    aoke
    0.08
     yourselves
    0.08
    ádu
    0.07
    usra
    0.07
    ographies
    0.07
    ersions
    0.07
    urrenc
    0.07
    ostel
    0.07
    ugas
    0.07
    Activations Density 0.000%

    No Known Activations