© 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. 120852
    Prev
    Next
    INDEX
    Explanations

    terms related to legal professions and practices

    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
    onet
    -0.08
    [OF
    -0.08
    ekler
    -0.07
    Ú¯ÛĮر
    -0.07
    hard
    -0.07
    sta
    -0.07
    azen
    -0.07
    gon
    -0.07
    IES
    -0.06
    å¶
    -0.06
    POSITIVE LOGITS
    ibaba
    0.07
    541
    0.06
     Bever
    0.05
    \Client
    0.05
     injury
    0.05
    _identity
    0.05
    edir
    0.05
    471
    0.05
    isclosed
    0.05
    lán
    0.05
    Activations Density 0.008%

    No Known Activations