© 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. 75218
    Prev
    Next
    INDEX
    Explanations

    Chat

    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_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
     Northwest
    -0.08
     Dodgers
    -0.07
     emlrt
    -0.07
     headers
    -0.07
    價
    -0.06
    "+
    -0.06
    ání
    -0.06
     PLA
    -0.06
    ile
    -0.06
     counts
    -0.06
    POSITIVE LOGITS
    iar
    0.06
     sayıda
    0.06
     Released
    0.06
     Shemale
    0.06
    atural
    0.06
    ีร
    0.06
     FLASH
    0.06
    ีช
    0.06
     birisi
    0.05
     cancellationToken
    0.05
    Activations Density 0.009%

    No Known Activations