© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 36928
    Prev
    Next
    INDEX
    Explanations

    technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     principal
    -0.06
     camps
    -0.06
     单
    -0.06
     Principal
    -0.06
    esterday
    -0.06
     undesirable
    -0.06
    	head
    -0.06
     squirt
    -0.06
     Casual
    -0.06
    بوب
    -0.06
    POSITIVE LOGITS
     QWidget
    0.07
    apyrus
    0.07
     sensed
    0.07
    nty
    0.07
    _blk
    0.06
    removeClass
    0.06
    '})↵
    0.06
     anlam
    0.06
    (Model
    0.06
     ülke
    0.06
    Activations Density 0.000%

    No Known Activations