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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 111893
    Prev
    Next
    INDEX
    Explanations

    words/stories/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
    .Sup
    -0.07
    :A
    -0.07
     DOWN
    -0.07
    (True
    -0.06
     Hero
    -0.06
     diseñador
    -0.06
    .it
    -0.06
    Gate
    -0.06
    .Template
    -0.06
    bil
    -0.06
    POSITIVE LOGITS
    cond
    0.07
    .roles
    0.06
    =document
    0.06
     internally
    0.06
    proj
    0.06
     parted
    0.06
    hound
    0.06
    cstring
    0.06
    vision
    0.06
     smelled
    0.06
    Activations Density 0.036%

    No Known Activations