© 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. 15276
    Prev
    Next
    INDEX
    Explanations

    words associated with division or conflict

    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
     Sahara
    -0.07
    ÛĮزÛĮ
    -0.06
    gnu
    -0.06
    esseract
    -0.06
    itud
    -0.06
    alsa
    -0.06
    avern
    -0.06
    loquent
    -0.06
    ä¾µ
    -0.06
    undra
    -0.06
    POSITIVE LOGITS
     violence
    0.07
    æ°ı
    0.07
    éric
    0.07
     competitiveness
    0.07
     Violence
    0.07
    ÑĢÑİ
    0.06
    CTR
    0.06
     fab
    0.06
    igu
    0.06
     communal
    0.06
    Activations Density 0.000%

    No Known Activations