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. 15-RESID-POST-AA
    6. 54032
    Prev
    Next
    INDEX
    Explanations

    Equation symbols

    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
    อท
    -0.07
     airports
    -0.07
    Juan
    -0.06
    management
    -0.06
    _files
    -0.06
     Assessment
    -0.06
    Cargo
    -0.06
     Rout
    -0.06
    river
    -0.06
    -door
    -0.06
    POSITIVE LOGITS
     edilen
    0.06
    (SQLException
    0.06
     Dhabi
    0.06
    (TRUE
    0.06
    _pipe
    0.06
    电子
    0.06
    �
    0.06
     높은
    0.06
    echn
    0.06
     gmail
    0.06
    Activations Density 0.020%

    No Known Activations