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. 50579
    Prev
    Next
    INDEX
    Explanations

    -type

    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
     finances
    -0.06
    616
    -0.06
     streams
    -0.06
     DbSet
    -0.06
    =os
    -0.06
    .allow
    -0.06
    .localization
    -0.06
     bs
    -0.06
    aseña
    -0.06
     dess
    -0.06
    POSITIVE LOGITS
     *\
    0.08
    діл
    0.07
    textView
    0.07
    -V
    0.07
     쉽
    0.07
     tư
    0.07
    _area
    0.07
    Flat
    0.07
    ecycle
    0.07
    	group
    0.07
    Activations Density 0.002%

    No Known Activations