© 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 EvalsExportsinterp-engineNEWAPI 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. 3048
    Prev
    Next
    INDEX
    Explanations

    occurrences of violent actions or discussions around conflict

    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
     addCriterion
    -0.08
    룴
    -0.07
     맥
    -0.06
    wine
    -0.06
     intox
    -0.06
    ammen
    -0.06
    DIM
    -0.06
    ioctl
    -0.06
    ersist
    -0.06
    podob
    -0.06
    POSITIVE LOGITS
    enthal
    0.07
     implements
    0.07
    quo
    0.06
    lemn
    0.06
    ìĭ¤
    0.06
    £½
    0.06
    /bit
    0.06
     unhappy
    0.06
    loquent
    0.06
     Aerospace
    0.06
    Activations Density 0.206%

    No Known Activations