© 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. 52890
    Prev
    Next
    INDEX
    Explanations

    Magic the Gathering cards

    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
     Niet
    -0.06
     jej
    -0.06
     flakes
    -0.06
    έν
    -0.06
     stake
    -0.06
    .trade
    -0.06
    inar
    -0.06
     locker
    -0.06
     esk
    -0.06
     yaşanan
    -0.06
    POSITIVE LOGITS
     TSRMLS
    0.07
     tük
    0.07
    ll
    0.06
    "%
    0.06
     вис
    0.06
    \Auth
    0.06
    /Library
    0.06
     activ
    0.06
     Aub
    0.06
    mot
    0.06
    Activations Density 0.007%

    No Known Activations