© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71937
    Prev
    Next
    INDEX
    Explanations

    mentions of ISIS and associated activities or individuals

    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
    fty
    -0.07
    oldem
    -0.07
     caffeine
    -0.07
    alker
    -0.07
    osit
    -0.07
     tea
    -0.06
    _Adjust
    -0.06
    ावन
    -0.06
     Tea
    -0.06
     Frid
    -0.06
    POSITIVE LOGITS
    usc
    0.07
     fitte
    0.07
     fatt
    0.07
    èī
    0.07
    éal
    0.07
     SEEK
    0.06
    surf
    0.06
    vat
    0.06
    (IS
    0.06
    .opendaylight
    0.06
    Activations Density 0.050%

    No Known Activations