© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60799
    Prev
    Next
    INDEX
    Explanations

    occurrences of events and event-related data in 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
     Neg
    -0.06
    ÅĻeb
    -0.06
    626
    -0.06
    330
    -0.06
     Pres
    -0.06
    642
    -0.06
    940
    -0.06
    ews
    -0.06
     pres
    -0.06
    SError
    -0.06
    POSITIVE LOGITS
    ilen
    0.07
     âĹĦ
    0.07
     Analog
    0.06
    AVING
    0.06
     Arms
    0.06
    orted
    0.06
    (GLFW
    0.06
    ARRANT
    0.06
    _INCLUDED
    0.06
    ãģ¯ãģļ
    0.06
    Activations Density 0.031%

    No Known Activations