© 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. 15-LLAMASCOPE-RES-131K
    11. 27144
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax

    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
    enty
    -0.06
    azio
    -0.06
     resid
    -0.06
    ">//
    -0.06
     Collapse
    -0.06
    ãĤ´ãĥª
    -0.06
    ós
    -0.06
    Jur
    -0.06
     Lands
    -0.06
     Expansion
    -0.06
    POSITIVE LOGITS
     Liberties
    0.08
    ubs
    0.07
    å¯Ħ
    0.07
    'gc
    0.07
    æľį
    0.07
    ruz
    0.06
    aggable
    0.06
    rane
    0.06
    pawn
    0.06
    -animate
    0.06
    Activations Density 0.024%

    No Known Activations