© 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. 17-LLAMASCOPE-RES-131K
    11. 71462
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to systems or circuits

    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
    IFO
    -0.07
    ί
    -0.07
    خب
    -0.07
    ÑĢий
    -0.07
     transmissions
    -0.06
    æk
    -0.06
    âĢ¦"↵↵
    -0.06
    .viewer
    -0.06
     Lover
    -0.06
    itia
    -0.06
    POSITIVE LOGITS
    ogn
    0.06
    ar
    0.06
    éĽª
    0.06
    lein
    0.06
    óc
    0.06
    507
    0.06
     Goldman
    0.06
    ics
    0.06
     isolation
    0.05
    ir
    0.05
    Activations Density 0.000%

    No Known Activations