© 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 (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 7678
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     declare
    -0.07
    ebe
    -0.07
     tome
    -0.07
    Customer
    -0.06
     AR
    -0.06
     世界
    -0.06
     workplace
    -0.06
     kicker
    -0.06
     Sağlık
    -0.06
     conclude
    -0.06
    POSITIVE LOGITS
    (木
    0.07
    حت
    0.07
    ра�
    0.06
    áhl
    0.06
    startup
    0.06
     heuristic
    0.06
    ("../../
    0.06
    klad
    0.06
    mamış
    0.06
    jian
    0.06
    Activations Density 0.090%

    No Known Activations