© 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. 97389
    Prev
    Next
    INDEX
    Explanations

    references to various types of explosions or explosive incidents

    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
    culate
    -0.07
    ethe
    -0.07
    inals
    -0.07
    estroy
    -0.07
    ete
    -0.06
    oller
    -0.06
    grav
    -0.06
    ingular
    -0.06
     Kings
    -0.06
    hei
    -0.06
    POSITIVE LOGITS
     vero
    0.06
    ázi
    0.06
    eel
    0.06
    nÃŃk
    0.06
     oprav
    0.06
    تب
    0.06
     tomb
    0.06
    ssc
    0.06
    _skip
    0.06
    ução
    0.06
    Activations Density 0.008%

    No Known Activations