© 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. 58501
    Prev
    Next
    INDEX
    Explanations

    phrases related to violence or fatal incidents

    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
     UnityEditor
    -0.07
    aid
    -0.07
     obce
    -0.07
    umi
    -0.07
    azo
    -0.07
    ór
    -0.07
    oose
    -0.07
    ICA
    -0.07
    atur
    -0.06
    isode
    -0.06
    POSITIVE LOGITS
     Francois
    0.06
     Slo
    0.06
    /host
    0.06
    ãģıãĤī
    0.06
     status
    0.06
    callable
    0.06
    AGER
    0.06
     slopes
    0.05
     Heck
    0.05
    ationToken
    0.05
    Activations Density 0.007%

    No Known Activations