© 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. 26883
    Prev
    Next
    INDEX
    Explanations

    method names and lifecycle callbacks 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
    oden
    -0.06
    klä
    -0.06
    orre
    -0.06
    lesia
    -0.06
    óm
    -0.06
    /dd
    -0.06
    herits
    -0.06
    steder
    -0.06
    existent
    -0.06
    owler
    -0.06
    POSITIVE LOGITS
    åľŃ
    0.07
     Wrath
    0.06
    lean
    0.06
    Bonjour
    0.06
    /host
    0.06
     Yük
    0.06
    LEAN
    0.06
    illo
    0.06
    еÑĢÑĪ
    0.06
    åľ¨åľ°
    0.06
    Activations Density 0.001%

    No Known Activations