© 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. 15-RESID-POST-AA
    6. 37022
    Prev
    Next
    INDEX
    Explanations

    Code/file paths

    np_max-act · gemini-2.0-flash

    identifiers and syntax patterns in system programming code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @andyrdt
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phillips
    -0.06
     Gardner
    -0.06
     Williams
    -0.06
     shepherd
    -0.06
    ана
    -0.06
    aktu
    -0.06
    aac
    -0.06
    demand
    -0.06
     içer
    -0.06
     подв
    -0.06
    POSITIVE LOGITS
     fert
    0.08
    取得
    0.07
    urv
    0.07
    oubtedly
    0.06
    ený
    0.06
    fails
    0.06
     diyor
    0.06
     showAlert
    0.06
     role
    0.06
    aneously
    0.06
    Activations Density 0.049%

    No Known Activations