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. 79786
    Prev
    Next
    INDEX
    Explanations

    distance

    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
    _disk
    -0.06
     whatsapp
    -0.06
    igeria
    -0.06
    接着
    -0.06
    ódigo
    -0.06
    Focused
    -0.06
    Phones
    -0.06
     swallowing
    -0.06
     sponsored
    -0.06
    1
    -0.06
    POSITIVE LOGITS
     clearfix
    0.07
     allele
    0.06
     adjust
    0.06
     lexer
    0.06
     през
    0.06
    Park
    0.06
    ‘s
    0.06
     echang
    0.06
     <$
    0.06
     vysok
    0.06
    Activations Density 0.023%

    No Known Activations