© 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. 124285
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to confidentiality and public access to documents

    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
     Záp
    -0.08
    pler
    -0.07
     Seks
    -0.07
    AMY
    -0.07
    ORIZED
    -0.07
    ucken
    -0.06
    å¡ļ
    -0.06
    UCKET
    -0.06
    inis
    -0.06
    ReuseIdentifier
    -0.06
    POSITIVE LOGITS
     sensitive
    0.10
    -sensitive
    0.08
     personal
    0.07
     sensitivity
    0.07
    asti
    0.07
    orsch
    0.07
    æķı
    0.07
    personal
    0.07
    ensitive
    0.06
     gist
    0.06
    Activations Density 0.009%

    No Known Activations