© 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 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. 17-LLAMASCOPE-RES-131K
    11. 130222
    Prev
    Next
    INDEX
    Explanations

    document sections related to project specifications and updates

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

    Terms indicating content status, version, or editorial modifications in published or distributed materials.

    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
     Carlson
    -0.07
    apiro
    -0.07
    ages
    -0.06
    Ñįй
    -0.06
     lia
    -0.06
    coin
    -0.06
    ieces
    -0.06
     Freund
    -0.06
    afort
    -0.06
    ëĵĿ
    -0.05
    POSITIVE LOGITS
     edition
    0.11
    çīĪ
    0.10
     Edition
    0.10
     version
    0.09
    version
    0.09
    edition
    0.09
     versión
    0.08
    omik
    0.08
     VERSION
    0.07
    xed
    0.07
    Activations Density 0.045%

    No Known Activations