© 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. 72065
    Prev
    Next
    INDEX
    Explanations

    references to societal division and the dichotomy of 'us' versus 'them'

    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
    atron
    -0.07
    ender
    -0.07
    oco
    -0.07
    pyx
    -0.07
    itud
    -0.06
    rie
    -0.06
    strup
    -0.06
    oren
    -0.06
    lero
    -0.06
     Stamp
    -0.06
    POSITIVE LOGITS
     foreign
    0.09
    foreign
    0.08
     foreigners
    0.07
     enemy
    0.07
    justify
    0.07
     آذ
    0.07
    .getTarget
    0.07
     targeting
    0.06
    Foreign
    0.06
     whom
    0.06
    Activations Density 0.026%

    No Known Activations