© 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. 17-LLAMASCOPE-RES-131K
    11. 123627
    Prev
    Next
    INDEX
    Explanations

    phrases related to software and system configuration

    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
     Ri
    -0.07
     Gol
    -0.06
    .fetch
    -0.06
    ObjectOfType
    -0.06
     Sv
    -0.06
    eno
    -0.06
    336
    -0.06
    alam
    -0.06
    é½
    -0.06
    antino
    -0.06
    POSITIVE LOGITS
    plode
    0.08
    elper
    0.08
    rais
    0.07
    Ģë¡ľ
    0.07
    ª
    0.07
    yonel
    0.07
    igos
    0.07
    edla
    0.07
    jpg
    0.07
    reader
    0.07
    Activations Density 0.015%

    No Known Activations