© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 50057
    Prev
    Next
    INDEX
    Explanations

    Adverbs of possibility/opinion

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Greeks
    -0.07
    _COLUMN
    -0.07
     Isles
    -0.07
    sav
    -0.06
    scheme
    -0.06
    (MAX
    -0.06
    ombat
    -0.06
     Их
    -0.06
    ’re
    -0.06
     Sweet
    -0.06
    POSITIVE LOGITS
    たちの
    0.07
     impover
    0.07
     periodic
    0.06
     проведення
    0.06
    енность
    0.06
    xampp
    0.06
    証
    0.06
    .Stderr
    0.06
    VisualStyleBackColor
    0.06
    .enterprise
    0.06
    Activations Density 0.201%

    No Known Activations