© 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. 58509
    Prev
    Next
    INDEX
    Explanations

    the name or variants of the name "Ab" in various contexts

    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
    /documentation
    -0.07
    insic
    -0.07
    ying
    -0.07
    yre
    -0.07
     лÑĸк
    -0.07
    تا
    -0.07
    yi
    -0.06
    antry
    -0.06
    osate
    -0.06
     MetroFramework
    -0.06
    POSITIVE LOGITS
    bie
    0.09
    igail
    0.09
    stractions
    0.08
    STRACT
    0.08
    OVE
    0.08
    bies
    0.07
    riel
    0.07
    sWith
    0.07
    err
    0.07
    iding
    0.07
    Activations Density 0.021%

    No Known Activations