© 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. 9-LLAMASCOPE-RES-131K
    11. 95656
    Prev
    Next
    INDEX
    Explanations

    elements related to color themes and visual aesthetics

    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
    les
    -0.07
    lander
    -0.06
    gross
    -0.06
     Musical
    -0.06
    sounds
    -0.06
     pand
    -0.06
     decltype
    -0.06
    648
    -0.06
    iap
    -0.06
    685
    -0.06
    POSITIVE LOGITS
    æĪ¶
    0.06
    _eof
    0.06
    ilst
    0.06
    主義
    0.06
    appa
    0.06
     éģ
    0.06
     æķ
    0.06
    ãĥ»ãĥ»ãĥ»↵↵
    0.06
    аза
    0.06
    ênh
    0.06
    Activations Density 0.006%

    No Known Activations