Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 21819
    Prev
    Next
    INDEX
    Explanations

    to

    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_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
    .En
    -0.07
    Lin
    -0.07
    in
    -0.07
     immigrants
    -0.07
     Human
    -0.07
     projector
    -0.07
    iam
    -0.07
    ich
    -0.06
    avorites
    -0.06
     Bien
    -0.06
    POSITIVE LOGITS
     đến
    0.07
    َ
    0.07
    ATO
    0.07
    造成
    0.07
    _PLATFORM
    0.06
     fruitful
    0.06
    _longitude
    0.06
    态
    0.06
     contrad
    0.06
    etler
    0.06
    Activations Density 0.026%

    No Known Activations