© 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. 40634
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or anger

    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
    æĭ¥
    -0.07
     ontvangst
    -0.07
    culate
    -0.07
    åĨ
    -0.07
     dikke
    -0.07
    VRT
    -0.06
    bris
    -0.06
    ernen
    -0.06
    multip
    -0.06
     kvin
    -0.06
    POSITIVE LOGITS
    ctors
    0.06
    ownt
    0.06
    inho
    0.06
    groupBy
    0.06
    load
    0.06
    iah
    0.06
    ahoma
    0.06
     Dank
    0.06
     off
    0.06
    帯
    0.06
    Activations Density 0.003%

    No Known Activations