© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92445
    Prev
    Next
    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive adjectival modifiers that classify or characterize the subject (e.g. “medium‐sized,” “urban,” “residential,” “snow-covered,” “liberal,” “centrist”).

    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
    -pos
    -0.07
    Ray
    -0.06
     endemic
    -0.06
    .An
    -0.06
    _".$
    -0.06
    -Mart
    -0.06
    �
    -0.06
    /download
    -0.06
     complementary
    -0.06
    روی
    -0.06
    POSITIVE LOGITS
     Trotsky
    0.07
    _putchar
    0.06
    烦
    0.06
     generalize
    0.06
     Able
    0.06
    皆
    0.06
     بيت
    0.06
    ै.↵
    0.06
    .chars
    0.06
    urface
    0.06
    Activations Density 0.072%

    No Known Activations