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. 7-RESID-POST-AA
    6. 93270
    Prev
    Next
    INDEX
    Explanations

    v

    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
    �
    -0.07
    dam
    -0.07
    +-+-+-+-
    -0.07
     disadv
    -0.06
     stad
    -0.06
    strcasecmp
    -0.06
    교회
    -0.06
     pointed
    -0.06
     marginTop
    -0.06
     Пло
    -0.06
    POSITIVE LOGITS
     youngster
    0.06
     T
    0.06
    Rick
    0.06
     sluggish
    0.06
    ्रश
    0.06
    اعية
    0.06
    THOOK
    0.06
     Its
    0.06
    "Oh
    0.06
     kaydet
    0.06
    Activations Density 0.001%

    No Known Activations