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. 93228
    Prev
    Next
    INDEX
    Explanations

    draft

    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
    =E
    -0.06
    discover
    -0.06
    .AutoSizeMode
    -0.06
     Ice
    -0.06
    =j
    -0.06
     syscall
    -0.06
    /node
    -0.06
     whistle
    -0.06
     Bee
    -0.06
    /system
    -0.06
    POSITIVE LOGITS
    τύ
    0.07
    ffff
    0.07
     июня
    0.07
     Draft
    0.07
     Knicks
    0.07
    JUnit
    0.07
     silky
    0.07
    承
    0.07
     Jury
    0.07
    modifiable
    0.06
    Activations Density 0.003%

    No Known Activations