Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29295
    Prev
    Next
    INDEX
    Explanations

    words related to casualties and injuries in violent events

    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
    gnore
    -0.09
     targetType
    -0.08
    481
    -0.07
     célib
    -0.07
    weetalert
    -0.07
    engan
    -0.07
    _TP
    -0.07
    anou
    -0.07
    entine
    -0.07
    assin
    -0.07
    POSITIVE LOGITS
     several
    0.09
     a
    0.08
     some
    0.08
     two
    0.08
     many
    0.08
     dozens
    0.08
     
    0.08
     an
    0.08
     one
    0.08
     en
    0.07
    Activations Density 0.011%

    No Known Activations