© 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. 17-LLAMASCOPE-RES-131K
    11. 71809
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols in text

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

    The conclusion of an answer in a Q&A format, typically appearing right before another answer begins or the thread ends.

    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
    Gui
    -0.06
    оз
    -0.06
    SKU
    -0.06
    seau
    -0.06
     Bryant
    -0.06
     Main
    -0.06
    agna
    -0.06
     Mou
    -0.06
    æīį
    -0.06
    keleton
    -0.06
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸв
    0.08
    zdy
    0.07
    çĶ³åįļ
    0.07
    ربÙĩ
    0.06
    μμ
    0.06
    .inline
    0.06
    edl
    0.06
    evi
    0.06
    riot
    0.06
     MetroFramework
    0.06
    Activations Density 0.015%

    No Known Activations