© 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. 42299
    Prev
    Next
    INDEX
    Explanations

    references to prisoners and their experiences or status

    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
    ROC
    -0.07
    cron
    -0.07
    irm
    -0.07
    大åħ¨
    -0.07
    bero
    -0.07
    cky
    -0.06
    ến
    -0.06
    amu
    -0.06
    aims
    -0.06
    .FlatStyle
    -0.06
    POSITIVE LOGITS
    hood
    0.10
    /sl
    0.09
    hips
    0.08
    ooter
    0.07
    oleon
    0.06
     Older
    0.06
     ëķ
    0.06
    ights
    0.06
     Laurel
    0.06
    /student
    0.06
    Activations Density 0.010%

    No Known Activations