© 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. 95485
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and official organizations

    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
    uss
    -0.07
    onn
    -0.07
    ikon
    -0.07
     æ¬
    -0.07
    à¸İ
    -0.06
    ipar
    -0.06
    ams
    -0.06
    wyn
    -0.06
    èħ
    -0.06
    egers
    -0.06
    POSITIVE LOGITS
    áo
    0.07
    oped
    0.06
    tml
    0.06
    ÅĻes
    0.06
    ided
    0.06
    owie
    0.06
    ÅĻed
    0.06
    ạt
    0.06
    415
    0.06
    ìłĿ
    0.06
    Activations Density 0.054%

    No Known Activations