© 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. 17340
    Prev
    Next
    INDEX
    Explanations

    references to excessive behavior or actions

    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
    sets
    -0.07
    ìłĿ
    -0.07
     ActiveSupport
    -0.07
    muz
    -0.07
    nier
    -0.07
    utex
    -0.07
    mie
    -0.07
    ri
    -0.07
    s
    -0.07
    usch
    -0.07
    POSITIVE LOGITS
     amounts
    0.11
     amount
    0.09
    amount
    0.08
    ately
    0.08
     reliance
    0.07
    /ext
    0.07
     sayıda
    0.07
     Amount
    0.07
    ively
    0.07
    -length
    0.07
    Activations Density 0.010%

    No Known Activations