© 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 EvalsExportsAPI 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. 125761
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal professionals and their activities

    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
     Cha
    -0.07
    amba
    -0.07
    Cha
    -0.07
    cha
    -0.07
    ober
    -0.06
     Stevenson
    -0.06
    inx
    -0.06
     Mature
    -0.06
     tying
    -0.06
     Occ
    -0.06
    POSITIVE LOGITS
    WindowText
    0.08
    Clients
    0.07
    LOCKS
    0.07
    getDisplay
    0.07
    undy
    0.07
     FAG
    0.07
    BALL
    0.06
    Å¡ov
    0.06
    .Interop
    0.06
    _MAGIC
    0.06
    Activations Density 0.003%

    No Known Activations