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. 81032
    Prev
    Next
    INDEX
    Explanations

    on

    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
    ・
    -0.06
    ---------------
    -0.06
    ----------------
    -0.06
    Tôi
    -0.06
     Fragment
    -0.06
    MBOL
    -0.06
    intent
    -0.06
    COVERY
    -0.06
    Billing
    -0.06
    (grammarAccess
    -0.06
    POSITIVE LOGITS
     xyz
    0.07
     탄
    0.07
    操
    0.06
     fprintf
    0.06
     diagrams
    0.06
     assms
    0.06
    '].$
    0.06
    _atual
    0.06
    .If
    0.06
     Mathf
    0.06
    Activations Density 0.050%

    No Known Activations