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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 87530
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations and opinions about movies and artistic works

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

    Hedging or qualifying language that limits the strength or absoluteness of statements, often indicating imperfection, partiality, or incompleteness.

    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
    orget
    -0.07
    oman
    -0.07
    gratis
    -0.06
    weetalert
    -0.06
     Poz
    -0.06
    crement
    -0.06
     *)((
    -0.06
    opis
    -0.06
    idir
    -0.06
    aba
    -0.06
    POSITIVE LOGITS
     nor
    0.16
     ani
    0.11
     Nor
    0.10
    Nor
    0.09
     anymore
    0.09
     neither
    0.08
     certainly
    0.08
     NOR
    0.07
    nor
    0.07
    à¹ģà¸Ļ
    0.07
    Activations Density 0.088%

    No Known Activations