© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 101420
    Prev
    Next
    INDEX
    Explanations

    /ajax

    np_max-act · gemini-2.0-flash

    non-technical content related to coding and web development examples.

    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
     Charter
    -0.07
    صال
    -0.07
    umbles
    -0.07
    ennis
    -0.07
    vy
    -0.07
     potrav
    -0.07
     Kurulu
    -0.07
    ้าของ
    -0.07
    abil
    -0.06
     facil
    -0.06
    POSITIVE LOGITS
    /ajax
    0.09
    ("$
    0.07
    长
    0.06
     recognition
    0.06
    .console
    0.06
    _structure
    0.06
     Interviews
    0.06
     ViewGroup
    0.06
    Identity
    0.06
    icontains
    0.06
    Activations Density 0.000%

    No Known Activations