© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62027
    Prev
    Next
    INDEX
    Explanations

    questions and discussions related to actions and intentions

    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
     Herrera
    -0.07
    ál
    -0.07
     Meadows
    -0.07
    äl
    -0.07
    isol
    -0.06
    unta
    -0.06
    WebKit
    -0.06
    abies
    -0.06
     Jako
    -0.06
    asl
    -0.06
    POSITIVE LOGITS
    oken
    0.07
    indow
    0.07
    ouser
    0.06
     Oz
    0.06
    kers
    0.06
    æ³ī
    0.06
     Millenn
    0.06
    istas
    0.06
    iseum
    0.06
    ska
    0.06
    Activations Density 0.006%

    No Known Activations