© 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. 27540
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to organizations or technologies

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

    Abbreviated terms, acronyms or proper names that appear in technical or specialized contexts.

    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
    illez
    -0.08
    edException
    -0.07
    elling
    -0.07
    ÙĨÙħ
    -0.07
    iyle
    -0.07
    Ĺi
    -0.07
    onica
    -0.07
    Ä°
    -0.07
    istan
    -0.07
    eding
    -0.07
    POSITIVE LOGITS
    teenth
    0.13
    zelf
    0.10
    zsche
    0.10
    ê¹
    0.09
    0.09
    ÅĽmy
    0.09
    ÑĤеÑģÑĮ
    0.08
    ÌĨ
    0.08
    ellaneous
    0.08
    bons
    0.08
    Activations Density 0.355%

    No Known Activations