© 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. 54936
    Prev
    Next
    INDEX
    Explanations

    instances of conflict or confrontation in social situations

    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
    zia
    -0.08
    é³´
    -0.08
    جار
    -0.08
    flen
    -0.08
    bx
    -0.08
    تس
    -0.07
    аÑĢÑĩ
    -0.07
    zÄĻ
    -0.07
    bach
    -0.07
    alus
    -0.07
    POSITIVE LOGITS
     private
    0.13
     alone
    0.12
     privately
    0.11
     confidential
    0.10
     aside
    0.10
     separate
    0.10
     isolated
    0.10
    alone
    0.10
     separately
    0.10
    private
    0.09
    Activations Density 0.051%

    No Known Activations