© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 20877
    Prev
    Next
    INDEX
    Explanations

    Pregnancy

    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
    _book
    -0.06
     Morse
    -0.06
     outfile
    -0.06
    Ten
    -0.06
     نف
    -0.06
    โท
    -0.06
     المع
    -0.06
    .mi
    -0.06
    佐
    -0.06
     livro
    -0.06
    POSITIVE LOGITS
     pregnant
    0.09
     \<
    0.08
     delivering
    0.08
     react
    0.07
    Direct
    0.07
    \<
    0.07
     Next
    0.07
     unstable
    0.07
     busy
    0.07
     meant
    0.07
    Activations Density 0.004%

    No Known Activations