© 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. 91322
    Prev
    Next
    INDEX
    Explanations

    code/technical language

    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
    ']").
    -0.08
    <State
    -0.07
     exemplary
    -0.06
     bouts
    -0.06
    ��
    -0.06
     quận
    -0.06
     नक
    -0.06
    beiten
    -0.06
     trấn
    -0.06
     반환
    -0.06
    POSITIVE LOGITS
    (abs
    0.07
    ="<?=
    0.06
     mains
    0.06
    .glide
    0.06
    κο
    0.06
     Sic
    0.06
     hour
    0.06
    _ARR
    0.06
    890
    0.06
    Spinner
    0.06
    Activations Density 0.001%

    No Known Activations