© 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. 62052
    Prev
    Next
    INDEX
    Explanations

    key metrics and parameters in mathematical models and algorithms

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

    Structural formatting tokens in academic papers, particularly punctuation, reference markers, and spacing that organize technical content.

    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
    _thumbnail
    -0.07
    egl
    -0.07
    apiro
    -0.06
    gth
    -0.06
    rips
    -0.06
    emente
    -0.06
    çİĦ
    -0.06
     Pil
    -0.06
    ette
    -0.06
    hydr
    -0.06
    POSITIVE LOGITS
    (IService
    0.06
     =",
    0.06
    pee
    0.06
    279
    0.06
    fra
    0.06
    -Allow
    0.06
    /Core
    0.06
    278
    0.05
    ouch
    0.05
    tober
    0.05
    Activations Density 0.022%

    No Known Activations