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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 110205
    Prev
    Next
    INDEX
    Explanations

    defamation lawsuits

    np_max-act · gemini-2.0-flash

    The neuron activates on words that signal legal or court‐related actions or claims (e.g. “injunction,” “published,” “allegations,” “lawsuit,” “defamation,” “damages”).

    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
    Tbl
    -0.08
    ocument
    -0.07
    uffy
    -0.07
     Ark
    -0.07
    UES
    -0.06
    eration
    -0.06
    sse
    -0.06
    ุงเทพมหานคร
    -0.06
    Increment
    -0.06
    isia
    -0.06
    POSITIVE LOGITS
    leneck
    0.08
     encountering
    0.07
     horrible
    0.07
     Cart
    0.06
    張
    0.06
    WiFi
    0.06
    ilecek
    0.06
    ほど
    0.06
    _generated
    0.06
     (!_
    0.06
    Activations Density 0.018%

    No Known Activations