© 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. 94249
    Prev
    Next
    INDEX
    Explanations

    instances of expressing dissatisfaction or complaints

    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
    ales
    -0.07
    åŀ
    -0.07
    ubat
    -0.06
     componentDid
    -0.06
    icari
    -0.06
    StreamReader
    -0.06
    orp
    -0.06
    κά
    -0.06
    lify
    -0.06
     brick
    -0.06
    POSITIVE LOGITS
     about
    0.09
    -about
    0.07
     Complaint
    0.07
     ABOUT
    0.07
    ingly
    0.07
     tentang
    0.07
     zbyt
    0.07
     complain
    0.07
     rằng
    0.06
    unct
    0.06
    Activations Density 0.009%

    No Known Activations