© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96825
    Prev
    Next
    INDEX
    Explanations

    specific events or incidents related to crime or 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
    loor
    -0.08
    stown
    -0.07
    eldo
    -0.07
    pdev
    -0.07
    anium
    -0.07
    adir
    -0.07
    ogui
    -0.07
    mekte
    -0.06
    hurst
    -0.06
    ulumi
    -0.06
    POSITIVE LOGITS
    ym
    0.06
    Haz
    0.06
    827
    0.06
    oste
    0.06
     Foley
    0.05
    Arena
    0.05
    ?url
    0.05
    zilla
    0.05
    omal
    0.05
     Player
    0.05
    Activations Density 0.001%

    No Known Activations