© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56632
    Prev
    Next
    INDEX
    Explanations

    terms related to violence and injuries

    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
     etc
    -0.09
    V
    -0.07
     Tato
    -0.06
    etc
    -0.06
    ir
    -0.06
    im
    -0.06
    /etc
    -0.06
    ãģĻãĤĮãģ°
    -0.06
    jac
    -0.06
    um
    -0.06
    POSITIVE LOGITS
     либо
    0.09
    either
    0.09
    rather
    0.08
    mostly
    0.08
     rather
    0.08
    although
    0.08
     either
    0.08
    exceptions
    0.08
    cctor
    0.08
     thôi
    0.08
    Activations Density 0.056%

    No Known Activations