© 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. 81428
    Prev
    Next
    INDEX
    Explanations

    themes involving coercion and threats related to crime and violence

    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
    805
    -0.08
    ÄŁa
    -0.07
    707
    -0.07
     gravy
    -0.07
    ãĤ¹ãĤ¯
    -0.06
    gregate
    -0.06
    arium
    -0.06
    803
    -0.06
    unner
    -0.06
    ched
    -0.06
    POSITIVE LOGITS
     force
    0.11
     gun
    0.11
     FORCE
    0.10
     Force
    0.10
    -gun
    0.09
    force
    0.09
    gun
    0.09
     threat
    0.08
     threats
    0.08
     Gun
    0.08
    Activations Density 0.051%

    No Known Activations