© 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. 9-LLAMASCOPE-RES-131K
    11. 98444
    Prev
    Next
    INDEX
    Explanations

    expressions related to argumentation and disagreement

    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
    LOTS
    -0.07
    سÙĨ
    -0.07
    Setter
    -0.07
    lag
    -0.06
    uem
    -0.06
    illet
    -0.06
    IFE
    -0.06
    ennial
    -0.06
    ique
    -0.06
    BuilderFactory
    -0.06
    POSITIVE LOGITS
    amon
    0.08
    recio
    0.06
    ÙĪÙĪ
    0.06
    à¹ĥà¸Ķ
    0.06
    elmet
    0.06
    egg
    0.06
    .invalid
    0.06
    atoon
    0.06
    ndata
    0.06
    adir
    0.06
    Activations Density 0.012%

    No Known Activations