© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 62442
    Prev
    Next
    INDEX
    Explanations

    key terms associated with portfolios and online marketplace interactions

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

    Repeated tokens or specific nouns that appear at transition points between content sections or in structured text like menus, code, or formatted 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
    ais
    -0.08
    inya
    -0.08
    uche
    -0.07
    agit
    -0.07
    째
    -0.07
    ichi
    -0.07
    hub
    -0.07
    uzey
    -0.07
    elsing
    -0.07
    avana
    -0.07
    POSITIVE LOGITS
     Fitzgerald
    0.07
    itals
    0.06
    odash
    0.06
     nghĩa
    0.06
    çĥĪ
    0.06
    zers
    0.06
     themed
    0.06
     Kun
    0.05
     alone
    0.05
    :UITableView
    0.05
    Activations Density 0.226%

    No Known Activations