© 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. 5-LLAMASCOPE-RES-131K
    11. 126050
    Prev
    Next
    INDEX
    Explanations

    references to the color white in descriptions of objects and decor

    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
    loub
    -0.07
    ucci
    -0.07
    usable
    -0.06
     Uncomment
    -0.06
    ross
    -0.06
    orsk
    -0.06
    ingroup
    -0.06
    infos
    -0.06
     oran
    -0.06
    uro
    -0.06
    POSITIVE LOGITS
    emap
    0.06
     Havana
    0.06
    enses
    0.06
    aille
    0.06
    CC
    0.06
    вий
    0.05
     вÑĤ
    0.05
     Om
    0.05
    رت
    0.05
    ụy
    0.05
    Activations Density 0.004%

    No Known Activations