© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 46434
    Prev
    Next
    INDEX
    Explanations

    row

    np_max-act · gemini-2.0-flash

    references to scientific models and theories related to particle physics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kode
    -0.07
     brisk
    -0.06
    airobi
    -0.06
    'id
    -0.06
     obedient
    -0.06
     davran
    -0.06
     berries
    -0.06
    ��
    -0.06
     IPL
    -0.06
    <m
    -0.06
    POSITIVE LOGITS
    움
    0.07
     웹
    0.06
     __________________
    0.06
    (matrix
    0.06
    “They
    0.06
    ((*
    0.06
    :view
    0.06
    _AMD
    0.06
    ตรว
    0.06
     HEADER
    0.06
    Activations Density 0.002%

    No Known Activations