© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93977
    Prev
    Next
    INDEX
    Explanations

    genetics

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tariff
    -0.07
     vm
    -0.07
     Oral
    -0.07
     vulnerable
    -0.07
    _prompt
    -0.06
    950
    -0.06
     transitioning
    -0.06
     Aş
    -0.06
     تل
    -0.06
     Trusted
    -0.06
    POSITIVE LOGITS
     genetics
    0.29
     Genetics
    0.21
    //*[
    0.07
     đình
    0.07
     С
    0.07
    enties
    0.06
     Scripture
    0.06
    نين
    0.06
    ;;;;;;;;;;;;;;;;
    0.06
    (title
    0.06
    Activations Density 0.002%

    No Known Activations