© 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. 31218
    Prev
    Next
    INDEX
    Explanations

    lexical items related to rebellion or defiance

    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
    imals
    -0.08
    obi
    -0.07
    enaire
    -0.07
    gang
    -0.07
    gere
    -0.07
    ãĤ¶
    -0.07
    oblin
    -0.07
    sel
    -0.07
    -valu
    -0.07
    finity
    -0.07
    POSITIVE LOGITS
    ution
    0.08
    /ref
    0.07
    ious
    0.07
    ito
    0.07
    231
    0.07
    atory
    0.07
    ino
    0.07
    ä¸ģ
    0.07
    bum
    0.06
    ance
    0.06
    Activations Density 0.004%

    No Known Activations