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. 104074
    Prev
    Next
    INDEX
    Explanations

    service

    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
    čin
    -0.08
    Austin
    -0.07
     Thick
    -0.07
     dwar
    -0.06
    “But
    -0.06
     акту
    -0.06
    analy
    -0.06
     Riv
    -0.06
    _depth
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     sním
    0.07
     строки
    0.07
    užel
    0.06
    appiness
    0.06
    (Unit
    0.06
     grandi
    0.06
    ξη
    0.06
    )d
    0.06
     "()
    0.06
    Getty
    0.05
    Activations Density 0.009%

    No Known Activations