Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 83255
    Prev
    Next
    INDEX
    Explanations

    The

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ерь
    -0.07
     sqlalchemy
    -0.07
    "And
    -0.06
     go
    -0.06
    	cursor
    -0.06
    ():↵↵
    -0.06
     Sample
    -0.06
    ısı
    -0.06
    “And
    -0.06
    ';
    ↵
    -0.06
    POSITIVE LOGITS
     expenditures
    0.06
     inflation
    0.06
     cumbersome
    0.06
    ModifiedDate
    0.06
     홍
    0.06
    bid
    0.06
    pher
    0.06
     measure
    0.06
    _factors
    0.06
    _operation
    0.06
    Activations Density 0.048%

    No Known Activations