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. 80589
    Prev
    Next
    INDEX
    Explanations

    load

    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
    .trailingAnchor
    -0.07
     Aristotle
    -0.07
    _exam
    -0.07
     бл
    -0.07
    开放
    -0.06
     пл
    -0.06
     Glouce
    -0.06
    _note
    -0.06
    '^
    -0.06
     reactionary
    -0.06
    POSITIVE LOGITS
     bring
    0.07
    iciary
    0.07
    ICI
    0.07
     Loaded
    0.07
     gracias
    0.06
    geist
    0.06
     :,
    0.06
     Load
    0.06
    pecial
    0.06
    mdl
    0.06
    Activations Density 0.027%

    No Known Activations