© 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. 104677
    Prev
    Next
    INDEX
    Explanations

    references to pranks and stunts

    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
    rint
    -0.08
    ãģĦãĤĭ
    -0.08
    pheric
    -0.08
    enze
    -0.08
    Äįe
    -0.08
    ẩn
    -0.08
    cÃŃm
    -0.08
    hood
    -0.07
    itches
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
    urs
    0.08
    iful
    0.07
    elog
    0.07
    ur
    0.06
     performed
    0.06
     Baz
    0.06
    Performed
    0.05
    u
    0.05
    astic
    0.05
     bay
    0.05
    Activations Density 0.001%

    No Known Activations