© 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. 62308
    Prev
    Next
    INDEX
    Explanations

    negations and phrases indicating the absence of something

    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
    2
    -0.06
    Äĥng
    -0.06
     not
    -0.06
     všechny
    -0.06
    imin
    -0.06
    sdale
    -0.06
     themselves
    -0.06
    ivery
    -0.06
    بد
    -0.06
     různé
    -0.06
    POSITIVE LOGITS
    bilt
    0.08
     evidence
    0.08
    occasion
    0.08
    .truth
    0.07
    /is
    0.07
    ади
    0.07
    eed
    0.07
    uelles
    0.07
    iversit
    0.07
    ogue
    0.07
    Activations Density 0.017%

    No Known Activations