© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98937
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to organizations or significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    so
    -0.18
    nya
    -0.18
    ness
    -0.17
    ne
    -0.17
    ìĿĦ
    -0.16
    sh
    -0.15
    ship
    -0.14
    son
    -0.14
    soft
    -0.14
    ss
    -0.13
    POSITIVE LOGITS
    urope
    0.11
    ÙĶ
    0.09
    eker
    0.08
    aux
    0.08
    equipment
    0.08
    ighbors
    0.08
    oxy
    0.07
    lessly
    0.07
    ois
    0.07
    oil
    0.07
    Activations Density 1.164%

    No Known Activations