© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 4946
    Prev
    Next
    INDEX
    Explanations

    arrest and legal context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incarceration
    -0.11
     incarcerated
    -0.10
     incarcer
    -0.10
    apg
    -0.09
    arcer
    -0.09
    amilia
    -0.09
     uninterrupted
    -0.09
    oust
    -0.08
    /Dk
    -0.08
     detainees
    -0.08
    POSITIVE LOGITS
     charged
    0.15
     wegen
    0.14
     Charg
    0.14
     charges
    0.14
    charged
    0.13
     charg
    0.13
     suspicion
    0.12
     accused
    0.12
    ees
    0.12
     connection
    0.11
    Activations Density 0.058%

    No Known Activations