© 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. 82096
    Prev
    Next
    INDEX
    Explanations

    phrases questioning the intelligence or motives of others

    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
    arde
    -0.07
    emoc
    -0.06
    590
    -0.06
    inic
    -0.06
    agog
    -0.06
    icket
    -0.06
    phans
    -0.06
    ilde
    -0.06
     å½
    -0.06
    init
    -0.06
    POSITIVE LOGITS
     seriously
    0.07
     Seriously
    0.07
     anyone
    0.07
     Serious
    0.07
    Seriously
    0.07
    ç«Ł
    0.07
    ëĿ½
    0.07
    _VM
    0.07
     vůbec
    0.06
    .actual
    0.06
    Activations Density 0.040%

    No Known Activations