© 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. 92290
    Prev
    Next
    INDEX
    Explanations

    phrases related to lawsuits and legal actions

    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
     à¤ħपर
    -0.07
    crime
    -0.07
    apeutic
    -0.07
     crime
    -0.07
     Prosecutor
    -0.07
    .habbo
    -0.06
    Ïĥμα
    -0.06
     Ribbon
    -0.06
     appellate
    -0.06
    _accessor
    -0.06
    POSITIVE LOGITS
     civil
    0.12
     Civil
    0.10
    civil
    0.09
    ivil
    0.09
     lawsuit
    0.09
    Civil
    0.09
     Suit
    0.09
     suit
    0.08
     sued
    0.08
     tort
    0.08
    Activations Density 0.025%

    No Known Activations