© 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. 9-LLAMASCOPE-RES-131K
    11. 97203
    Prev
    Next
    INDEX
    Explanations

    terms related to legal professionals and the costs associated with legal services

    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
    laus
    -0.08
    avar
    -0.07
    ucha
    -0.06
    uela
    -0.06
    steen
    -0.06
     rozum
    -0.06
     itself
    -0.06
    pen
    -0.06
    缼
    -0.06
    lies
    -0.06
    POSITIVE LOGITS
    chein
    0.07
    iken
    0.06
    bote
    0.06
    edis
    0.06
    panied
    0.06
     次
    0.06
    Prot
    0.06
    are
    0.06
     forbidden
    0.06
    onces
    0.06
    Activations Density 0.011%

    No Known Activations