© 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. 82575
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
    eton
    -0.07
    subtype
    -0.07
    /null
    -0.07
    entai
    -0.07
    esson
    -0.06
    дÑĥ
    -0.06
    assen
    -0.06
    жи
    -0.06
    erson
    -0.06
    érie
    -0.06
    POSITIVE LOGITS
    ToPoint
    0.07
    ValuePair
    0.06
    WithValue
    0.06
    ikon
    0.06
    beck
    0.06
    suite
    0.06
    ghest
    0.06
    riminator
    0.06
     поÑģÑĤанов
    0.06
    LAR
    0.06
    Activations Density 0.074%

    No Known Activations