© 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. 17-LLAMASCOPE-RES-131K
    11. 85638
    Prev
    Next
    INDEX
    Explanations

    phrases related to crime and 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
    utow
    -0.07
    arsi
    -0.07
    Crit
    -0.07
    nesc
    -0.07
    uner
    -0.07
    ezier
    -0.07
    crit
    -0.06
     पà¤ķ
    -0.06
    -www
    -0.06
    èm
    -0.06
    POSITIVE LOGITS
     Blanch
    0.06
    esk
    0.06
     yesterday
    0.06
     вел
    0.06
     motive
    0.06
    èģŀ
    0.06
    erton
    0.06
     puzzles
    0.06
     sad
    0.06
     quiet
    0.06
    Activations Density 0.014%

    No Known Activations