© 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. 15-LLAMASCOPE-RES-131K
    11. 86889
    Prev
    Next
    INDEX
    Explanations

    the word "where" 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
    heimer
    -0.09
    agger
    -0.07
    ags
    -0.07
    åħ¸
    -0.07
    cken
    -0.07
    anca
    -0.07
    ately
    -0.07
    ceae
    -0.07
    irie
    -0.07
    ador
    -0.07
    POSITIVE LOGITS
     it
    0.08
     they
    0.08
    oping
    0.07
    upon
    0.07
     he
    0.06
    dan
    0.06
    mür
    0.06
    _gp
    0.05
    902
    0.05
     we
    0.05
    Activations Density 0.019%

    No Known Activations