© 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. 62890
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Tom"

    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
    yen
    -0.08
    izr
    -0.08
    äºŃ
    -0.07
    licht
    -0.07
    umuz
    -0.07
    ABLE
    -0.07
    ept
    -0.07
    ableObject
    -0.07
    edm
    -0.07
    ubby
    -0.07
    POSITIVE LOGITS
    mas
    0.09
    cat
    0.09
    orrow
    0.08
    islav
    0.08
    atoes
    0.08
    my
    0.07
    kins
    0.07
    ma
    0.07
    Tom
    0.07
    äºĭ
    0.07
    Activations Density 0.009%

    No Known Activations