© 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. 78326
    Prev
    Next
    INDEX
    Explanations

    variables and function names related to app configuration and data handling

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

    Variable or placeholder values in code, often used in test cases, configuration files, or application data structures - particularly in contexts where values are being compared, initialized, or representing default/test data.

    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
     (
    -0.07
     Sexe
    -0.06
    avenport
    -0.06
     valide
    -0.06
    redo
    -0.06
    ichte
    -0.06
     medi
    -0.06
     Dane
    -0.06
    itag
    -0.06
    illi
    -0.06
    POSITIVE LOGITS
    stüt
    0.07
    LEGRO
    0.07
    123
    0.07
    arna
    0.07
    acus
    0.06
    iÅŁtir
    0.06
    _TOUCH
    0.06
    roker
    0.06
    _exempt
    0.06
    (@(
    0.06
    Activations Density 0.027%

    No Known Activations