© 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. 26831
    Prev
    Next
    INDEX
    Explanations

    references to parts or segments of a series or collection

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

    References to numbered or sequential parts of multi-part content (articles, series, albums, books) that indicate how larger works are divided.

    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
     Compatible
    -0.06
     Nich
    -0.06
    ade
    -0.06
    سÙĦ
    -0.06
    AGAIN
    -0.06
    дин
    -0.05
     Kund
    -0.05
     Quinn
    -0.05
    _FF
    -0.05
    zin
    -0.05
    POSITIVE LOGITS
     Part
    0.08
    KeySpec
    0.07
     Parts
    0.07
    edn
    0.07
    omap
    0.07
    cul
    0.07
    Parts
    0.07
    BorderStyle
    0.07
    panion
    0.07
     ÑĩаÑģÑĤи
    0.07
    Activations Density 0.016%

    No Known Activations