© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87394
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Function or method return values or closing delimiters at the end of function definitions in code.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    lect
    -0.07
    üstü
    -0.06
    iston
    -0.06
    @@
    -0.06
    amed
    -0.05
    er
    -0.05
     stir
    -0.05
    ulet
    -0.05
    ozem
    -0.05
    conti
    -0.05
    POSITIVE LOGITS
    _example
    0.08
     examples
    0.07
     benchmark
    0.07
     example
    0.07
    WAYS
    0.07
    ets
    0.07
     Examples
    0.07
    ANNER
    0.07
    Examples
    0.07
     Benchmark
    0.07
    Activations Density 0.009%

    No Known Activations