© 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. 123719
    Prev
    Next
    INDEX
    Explanations

    themes of manipulation and coercion in interactions

    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
    ederation
    -0.07
    ((↵
    -0.06
    elerde
    -0.06
    çľģ
    -0.06
    rovers
    -0.06
    inline
    -0.06
    ikel
    -0.06
     Twins
    -0.06
     Pew
    -0.06
    æĸ
    -0.06
    POSITIVE LOGITS
     blackmail
    0.11
     threatened
    0.10
     threats
    0.09
     threatening
    0.09
     threatens
    0.09
     threaten
    0.09
     threat
    0.08
     Threat
    0.08
    threat
    0.08
    -threat
    0.07
    Activations Density 0.009%

    No Known Activations