© 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. 15-RESID-POST-AA
    11. 92905
    Prev
    Next
    INDEX
    Explanations

    Java class names ending in -er

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $",
    -0.07
    úp
    -0.07
    /{{
    -0.07
     highlight
    -0.07
    องท
    -0.06
    ิท
    -0.06
    估
    -0.06
     `.
    -0.06
    .future
    -0.06
    >,</
    -0.06
    POSITIVE LOGITS
     Mus
    0.06
     reasoning
    0.06
     Puppy
    0.06
     NEO
    0.06
    STATIC
    0.06
     passphrase
    0.06
    blick
    0.06
    Prince
    0.06
    InternalEnumerator
    0.05
    cessive
    0.05
    Activations Density 0.015%

    No Known Activations