© 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. 78117
    Prev
    Next
    INDEX
    Explanations

    verbs related to involvement in organizational activities and responsibilities

    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
    |{↵
    -0.09
    ught
    -0.08
    isposable
    -0.07
     DependencyProperty
    -0.07
    .scalablytyped
    -0.07
    IIIK
    -0.07
     právÄĽ
    -0.07
     '{@
    -0.07
    oca
    -0.07
     membr
    -0.07
    POSITIVE LOGITS
     etc
    0.09
    ãģĿãģĹãģ¦
    0.08
     ìŀĪê³ł
    0.08
     ê·¸ë¦¬ê³ł
    0.07
    tol
    0.07
     pedig
    0.07
     ÑĤоÑīо
    0.06
    !!,
    0.06
     and
    0.06
    å¡
    0.06
    Activations Density 0.281%

    No Known Activations