© 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. 118584
    Prev
    Next
    INDEX
    Explanations

    terms related to creativity and its intersection with mental health, particularly bipolar disorder

    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
    lew
    -0.07
    à¹Ĩ
    -0.06
    ensively
    -0.06
    Ø¡
    -0.06
    soever
    -0.06
    -origin
    -0.06
     reverse
    -0.06
    uforia
    -0.06
    lessly
    -0.05
    POSITIVE LOGITS
    âĢ¦↵↵↵
    0.11
    -related
    0.09
    berman
    0.08
     pione
    0.08
    린ìĿ´
    0.07
    updatedAt
    0.07
    ovan
    0.07
     kav
    0.07
    Ãło
    0.07
    ãĥ
    0.07
    Activations Density 1.755%

    No Known Activations