© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 73681
    Prev
    Next
    INDEX
    Explanations

    adding information

    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
    Patch
    -0.07
    _props
    -0.07
     coax
    -0.06
     Powder
    -0.06
     виконав
    -0.06
    .apache
    -0.06
    .Av
    -0.06
     box
    -0.06
    ostat
    -0.06
     iterating
    -0.06
    POSITIVE LOGITS
     hors
    0.06
     YORK
    0.06
     �
    0.06
    |m
    0.06
     😉
    0.06
    。而
    0.06
     ISSUE
    0.05
     )
    0.05
    ‌ها
    0.05
     болез
    0.05
    Activations Density 0.025%

    No Known Activations