© 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. 15-LLAMASCOPE-RES-131K
    11. 26871
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to coding logic and structure

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

    Code comments preceded by double forward slashes (//) in programming languages. They often appear before or after code statements to provide explanations or documentation.

    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
    ucci
    -0.08
    haps
    -0.07
    apiro
    -0.07
    orer
    -0.06
    angu
    -0.06
    úp
    -0.06
    arat
    -0.06
    @s
    -0.06
     Flam
    -0.06
    anted
    -0.05
    POSITIVE LOGITS
    llib
    0.09
    iley
    0.08
    $MESS
    0.08
    evin
    0.07
    EventManager
    0.07
    anner
    0.06
    न
    0.06
    <source
    0.06
    ÙĨع
    0.06
    agina
    0.06
    Activations Density 0.040%

    No Known Activations