© 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. 83944
    Prev
    Next
    INDEX
    Explanations

    method calls or function execution 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
    EMA
    -0.07
    394
    -0.07
    ema
    -0.06
    اض
    -0.06
    chner
    -0.06
    wik
    -0.06
    uch
    -0.06
    irk
    -0.06
    ÑĢÑı
    -0.06
     Hole
    -0.06
    POSITIVE LOGITS
     exit
    0.08
     quitting
    0.08
    endcode
    0.07
    ediator
    0.07
    .mainloop
    0.07
    .exit
    0.07
    itore
    0.07
    egen
    0.07
    ephir
    0.07
    RunLoop
    0.07
    Activations Density 0.023%

    No Known Activations