© 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. 15-RESID-POST-AA
    11. 34342
    Prev
    Next
    INDEX
    Explanations

    Questions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cancel
    -0.07
     rhetoric
    -0.07
     arriv
    -0.07
     dips
    -0.07
     cooperate
    -0.07
     Sal
    -0.07
     entertain
    -0.06
    weight
    -0.06
     Ian
    -0.06
     descri
    -0.06
    POSITIVE LOGITS
    .…
    0.06
    SKTOP
    0.06
     stdClass
    0.06
     Đài
    0.06
     '))↵
    0.06
     THREE
    0.06
     سایر
    0.06
     ناح
    0.06
    arently
    0.06
     OVERRIDE
    0.06
    Activations Density 0.115%

    No Known Activations