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. 54284
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     RH
    -0.06
    =\"$
    -0.06
     encontrado
    -0.06
     authService
    -0.06
    #{@
    -0.06
    Building
    -0.06
     hdc
    -0.06
     ipc
    -0.06
     hộp
    -0.05
    (',')↵
    -0.05
    POSITIVE LOGITS
    ssi
    0.07
    HZ
    0.06
    Program
    0.06
    ,j
    0.06
    지역
    0.06
    one
    0.06
    �
    0.06
    ,GL
    0.06
    住
    0.06
     котор
    0.06
    Activations Density 0.000%

    No Known Activations