© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74743
    Prev
    Next
    INDEX
    Explanations

    allegations, accusations, charges

    np_max-act · gemini-2.0-flash

    The neuron activates on legal/judicial terminology relating to filings, charges, lawsuits, or allegations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ーション
    -0.07
    arLayout
    -0.06
    homes
    -0.06
    chedulers
    -0.06
     transportation
    -0.06
     články
    -0.06
     })↵
    -0.06
    .append
    -0.06
     worst
    -0.06
    Australia
    -0.06
    POSITIVE LOGITS
     Birch
    0.08
    GORITH
    0.08
    .setEditable
    0.07
    arhus
    0.07
    ystick
    0.07
     deutsch
    0.07
     жир
    0.07
     enfermed
    0.06
    -air
    0.06
     первого
    0.06
    Activations Density 0.030%

    No Known Activations