Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8187
    Prev
    Next
    INDEX
    Explanations

    Court/crime news articles

    np_max-act · gemini-2.0-flash

    incidents involving criminal activity and legal consequences.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on language describing legal proceedings—mentions of courts, sentencing, pleas, jail terms, and related prosecution details.

    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
     عباس
    -0.07
    .invoice
    -0.06
    redict
    -0.06
    шли
    -0.06
    ита
    -0.06
    exit
    -0.06
    لمه
    -0.06
    šky
    -0.06
    treeview
    -0.06
     repaint
    -0.06
    POSITIVE LOGITS
    piel
    0.07
    186
    0.06
    .Can
    0.06
     setHidden
    0.06
     inhibitors
    0.06
    aturally
    0.06
    .populate
    0.06
    _First
    0.06
    Could
    0.06
     welcomes
    0.06
    Activations Density 0.013%

    No Known Activations