© 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. 61794
    Prev
    Next
    INDEX
    Explanations

    references to organization, company, or institutional identity

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

    Text segments that serve as website navigation elements or organizational content labels, particularly those describing company/organization identity or linking between sections.

    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
    ÑĢок
    -0.07
    UserCode
    -0.07
    ehler
    -0.06
    enes
    -0.06
    hibit
    -0.06
    ↵↵
    -0.06
    岸
    -0.06
    notated
    -0.06
    neau
    -0.06
    anteed
    -0.06
    POSITIVE LOGITS
     background
    0.10
    background
    0.09
     Background
    0.09
     history
    0.08
     About
    0.08
    /history
    0.07
    (background
    0.07
    Background
    0.07
    -background
    0.07
    .about
    0.07
    Activations Density 0.036%

    No Known Activations