© 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. 62903
    Prev
    Next
    INDEX
    Explanations

    references to weapons and threats of 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
    icast
    -0.07
    ilio
    -0.06
    à¹Ĥà¸Ļ
    -0.06
     fists
    -0.06
    usercontent
    -0.06
    oho
    -0.06
    apa
    -0.06
    incare
    -0.06
    eo
    -0.06
    pedia
    -0.06
    POSITIVE LOGITS
     threatening
    0.08
     threat
    0.08
    threat
    0.07
    ì´Ŀ
    0.07
     threats
    0.07
    held
    0.07
    shelf
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.07
    amar
    0.06
     Threat
    0.06
    Activations Density 0.011%

    No Known Activations