© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    function and method declarations in programming code

    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
    alls
    -0.07
    (always
    -0.06
    æīĵ
    -0.06
    egra
    -0.06
     Kem
    -0.06
     Faster
    -0.06
    lesia
    -0.06
    çĵ
    -0.06
    898
    -0.06
    icago
    -0.06
    POSITIVE LOGITS
     Robbins
    0.07
    .pen
    0.07
    Å¡t
    0.06
    asse
    0.06
    ute
    0.06
    üc
    0.06
    igon
    0.06
    tol
    0.06
    ãĥ¼ãĥĪ
    0.06
    agal
    0.06
    Activations Density 0.007%

    No Known Activations