© 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. 19-RESID-POST-AA
    11. 52034
    Prev
    Next
    INDEX
    Explanations

    Informal speech

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    X
    -0.08
    Here
    -0.08
     backs
    -0.06
    tréal
    -0.06
    Detector
    -0.06
     Week
    -0.06
    overnment
    -0.06
    _sm
    -0.06
    _TRAN
    -0.06
    Regions
    -0.06
    POSITIVE LOGITS
     cricket
    0.06
     practically
    0.06
     araştır
    0.06
     Yer
    0.06
     beaut
    0.06
     undercut
    0.06
    Od
    0.06
     pancreatic
    0.06
    ิกายน
    0.06
     maxValue
    0.06
    Activations Density 0.043%

    No Known Activations