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. 11-RESID-POST-AA
    6. 81291
    Prev
    Next
    INDEX
    Explanations

    Schedules/courses

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hal
    -0.06
    _geo
    -0.06
    \Customer
    -0.06
     Palmer
    -0.06
     images
    -0.06
     đ�
    -0.06
    -image
    -0.06
     pertinent
    -0.06
    -menu
    -0.06
    answers
    -0.06
    POSITIVE LOGITS
     skuteč
    0.06
     Stability
    0.06
    ché
    0.06
     campaigning
    0.06
    _DECLS
    0.06
     zengin
    0.06
     ck
    0.06
     یکی
    0.06
    _K
    0.06
     jusqu
    0.06
    Activations Density 0.020%

    No Known Activations