Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19778
    Prev
    Next
    INDEX
    Explanations

    share

    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
     zipper
    -0.07
    .quest
    -0.07
    (T
    -0.07
    Т
    -0.07
     comida
    -0.07
     ocean
    -0.07
    (dictionary
    -0.07
     pont
    -0.06
    :id
    -0.06
     ölüm
    -0.06
    POSITIVE LOGITS
    her
    0.08
     shareholders
    0.08
     shake
    0.08
    shake
    0.07
     Share
    0.07
     Shares
    0.07
    has
    0.07
    les
    0.07
    Share
    0.07
    are
    0.07
    Activations Density 0.008%

    No Known Activations