© 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. 41643
    Prev
    Next
    INDEX
    Explanations

    jav

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the “Generated by javadoc” header line (i.e. the Javadoc boilerplate that shows when a page was auto‐generated).

    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
     dto
    -0.07
    undo
    -0.07
     Protestant
    -0.07
    ache
    -0.06
     svém
    -0.06
    cete
    -0.06
    zeros
    -0.06
     incentives
    -0.06
    ^{
    -0.06
     jiný
    -0.06
    POSITIVE LOGITS
    jections
    0.07
    869
    0.06
    ActivityResult
    0.06
    овано
    0.06
    旁
    0.06
     QVBoxLayout
    0.06
     ranges
    0.06
    ủng
    0.06
    """↵↵
    0.06
    _PIX
    0.06
    Activations Density 0.000%

    No Known Activations