© 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. 92194
    Prev
    Next
    INDEX
    Explanations

    phrases or structures related to legal and regulatory contexts

    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
    akistan
    -0.07
    461
    -0.07
    _dbg
    -0.06
    oppable
    -0.06
    âng
    -0.06
    ITHER
    -0.06
    ĵåIJį
    -0.06
    ackers
    -0.06
    .InnerException
    -0.06
    rug
    -0.06
    POSITIVE LOGITS
    .misc
    0.08
    ayd
    0.07
     Misc
    0.06
    rowse
    0.06
    Misc
    0.06
    #ac
    0.06
    .jms
    0.06
    suite
    0.06
    ClassLoader
    0.06
    quil
    0.06
    Activations Density 0.001%

    No Known Activations