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. 7-RESID-POST-AA
    6. 70165
    Prev
    Next
    INDEX
    Explanations

    2

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (pid
    -0.06
    'S
    -0.06
     lider
    -0.06
    >>::
    -0.06
     centrif
    -0.06
    ımıza
    -0.06
    -negative
    -0.06
     solicit
    -0.06
    uely
    -0.06
    (trim
    -0.06
    POSITIVE LOGITS
    2
    0.08
     Reviewed
    0.07
     Weather
    0.07
    board
    0.06
    ök
    0.06
    Tests
    0.06
    oyer
    0.06
    acers
    0.06
     Butler
    0.06
    Hundreds
    0.06
    Activations Density 0.018%

    No Known Activations