© 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. 98914
    Prev
    Next
    INDEX
    Explanations

    programming logic and conditional checks

    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
    ertino
    -0.07
    ogenerated
    -0.07
    imest
    -0.07
    lash
    -0.07
    bu
    -0.06
    oret
    -0.06
    834
    -0.06
    Ư
    -0.06
    abcdefghijklmnop
    -0.06
    reon
    -0.06
    POSITIVE LOGITS
    ady
    0.07
    ãĤ¸ãĤ¢
    0.06
    ecz
    0.06
     Roch
    0.06
     Transparent
    0.06
    Transparent
    0.06
    instrument
    0.06
    ãģĮåĩº
    0.05
    .EventArgs
    0.05
    accom
    0.05
    Activations Density 0.036%

    No Known Activations