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. 3-RESID-POST-AA
    6. 94722
    Prev
    Next
    INDEX
    Explanations

    transformed

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     c
    -0.07
    _SIDE
    -0.07
     Asking
    -0.06
     draw
    -0.06
    (play
    -0.06
     "{"
    -0.06
    avery
    -0.06
     open
    -0.06
     precedence
    -0.06
     width
    -0.06
    POSITIVE LOGITS
     transformed
    0.19
     transformation
    0.09
     transforms
    0.09
     transforming
    0.09
     makeover
    0.08
     ロ
    0.08
     Philips
    0.07
     contrato
    0.07
     transform
    0.07
     Transform
    0.07
    Activations Density 0.017%

    No Known Activations