© 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. 126081
    Prev
    Next
    INDEX
    Explanations

    phrases and imagery related to light

    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
    \views
    -0.08
    еÑĢк
    -0.06
    راÙģ
    -0.06
     fetching
    -0.06
    /assert
    -0.06
    ÑĤал
    -0.06
     pitch
    -0.06
    vertiser
    -0.06
     redundant
    -0.06
    èĵ
    -0.06
    POSITIVE LOGITS
    phan
    0.06
    Tx
    0.06
    pher
    0.06
    iams
    0.06
    Ãĵ
    0.06
     Markt
    0.06
     Hans
    0.06
    olin
    0.06
    zu
    0.06
    125
    0.06
    Activations Density 0.002%

    No Known Activations