© 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. 847
    Prev
    Next
    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash

    The neuron activates on the numeric components of legal case citations (the volume and page numbers in reporter citations).

    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
    		↵	↵
    -0.06
    انگ
    -0.06
     -/↵
    -0.06
    .addr
    -0.06
     Manor
    -0.06
     nouve
    -0.06
    圖
    -0.06
     Assy
    -0.06
    Bat
    -0.06
     Shoes
    -0.06
    POSITIVE LOGITS
     Objective
    0.07
    NSData
    0.06
    _check
    0.06
     Penalty
    0.06
    toInt
    0.06
    _settings
    0.06
    esser
    0.06
     momentarily
    0.06
     أم
    0.06
    /create
    0.06
    Activations Density 0.002%

    No Known Activations