© 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. 94125
    Prev
    Next
    INDEX
    Explanations

    references to bipolar disorder and its relationship with creativity

    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
    olatile
    -0.09
    anax
    -0.08
    LOUD
    -0.08
    OLT
    -0.08
    wner
    -0.08
    NCY
    -0.08
    анÑĤаж
    -0.08
    èĬ³
    -0.07
    gressor
    -0.07
    enet
    -0.07
    POSITIVE LOGITS
     Ant
    0.07
     ham
    0.06
     Ham
    0.06
     Hamilton
    0.06
     Johns
    0.06
     ab
    0.06
    0.06
     un
    0.06
     Helena
    0.06
     an
    0.05
    Activations Density 0.002%

    No Known Activations