© 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. 93395
    Prev
    Next
    INDEX
    Explanations

    references to gun violence and shootings

    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
    azor
    -0.06
    uner
    -0.06
     quantitative
    -0.06
    ouve
    -0.06
    aed
    -0.06
    aktion
    -0.06
    actly
    -0.06
    862
    -0.06
     Act
    -0.06
     tick
    -0.06
    POSITIVE LOGITS
    ábado
    0.07
    AGMA
    0.07
    .partition
    0.07
     Hole
    0.07
    _reply
    0.07
    lamaya
    0.06
    bac
    0.06
    (OS
    0.06
    ILLISECONDS
    0.06
     ontvangst
    0.06
    Activations Density 0.013%

    No Known Activations