© 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. 116782
    Prev
    Next
    INDEX
    Explanations

    references to prison sentences and incarceration

    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
    eyim
    -0.07
    \Doctrine
    -0.07
    ´Ŀ
    -0.07
    osu
    -0.06
    reator
    -0.06
     Wikip
    -0.06
    ̧
    -0.06
    olley
    -0.06
    .Formatting
    -0.06
    úi
    -0.06
    POSITIVE LOGITS
    utter
    0.08
    aper
    0.07
     plus
    0.07
     followed
    0.07
    kp
    0.07
    .cg
    0.06
    plus
    0.06
    jong
    0.06
    ipel
    0.06
    bas
    0.06
    Activations Density 0.005%

    No Known Activations