© 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. 119469
    Prev
    Next
    INDEX
    Explanations

    references to character development in narrative contexts

    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
    ÑĩаÑģ
    -0.09
    xDB
    -0.08
    ILT
    -0.08
     Hüs
    -0.08
    ä¸ĺ
    -0.08
     listBox
    -0.07
    uien
    -0.07
    одо
    -0.07
    å¹¹
    -0.07
    ç´ł
    -0.07
    POSITIVE LOGITS
     life
    0.08
     various
    0.08
     journey
    0.08
     experiences
    0.08
     how
    0.08
     struggle
    0.08
     along
    0.07
     reactions
    0.07
     attempts
    0.07
     gradually
    0.07
    Activations Density 0.035%

    No Known Activations