© 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. 19-RESID-POST-AA
    11. 87328
    Prev
    Next
    INDEX
    Explanations

    is

    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
     گذشته
    -0.07
     deeper
    -0.06
     mulheres
    -0.06
    кид
    -0.06
     variants
    -0.06
     người
    -0.06
     anything
    -0.06
     dalla
    -0.06
     reven
    -0.06
     Rocket
    -0.06
    POSITIVE LOGITS
    is
    0.08
     инфек
    0.07
    	tp
    0.06
    IS
    0.06
    �프
    0.06
     �
    0.06
    ชอบ
    0.06
    inside
    0.06
    _perc
    0.06
     προσ
    0.06
    Activations Density 0.007%

    No Known Activations