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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 104429
    Prev
    Next
    INDEX
    Explanations

    cath

    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
     운
    -0.08
     Und
    -0.07
     Ryder
    -0.07
    ่วง
    -0.07
     英
    -0.07
     曰
    -0.06
     weir
    -0.06
    Und
    -0.06
     RECORD
    -0.06
    andan
    -0.06
    POSITIVE LOGITS
     Cath
    0.14
     cath
    0.12
     Katherine
    0.09
     Kathy
    0.09
     Cathy
    0.09
     Kath
    0.09
     Catherine
    0.08
     Nath
    0.08
     Katie
    0.08
    ath
    0.07
    Activations Density 0.007%

    No Known Activations