© 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. 27358
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal claims and emotional distress in the context of personal injury or divorce cases

    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
    azzi
    -0.08
    ouri
    -0.08
    vron
    -0.07
    ucu
    -0.07
    izin
    -0.07
    ppv
    -0.07
    ennie
    -0.07
    aku
    -0.07
    \Exception
    -0.07
    foy
    -0.07
    POSITIVE LOGITS
    ¿
    0.06
     cad
    0.06
    _MON
    0.06
    uteur
    0.06
     Hindered
    0.06
    mando
    0.06
     pros
    0.06
     moral
    0.06
     dut
    0.05
    .gstatic
    0.05
    Activations Density 0.001%

    No Known Activations