© 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. 3-RESID-POST-AA
    11. 94060
    Prev
    Next
    INDEX
    Explanations

    расп

    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
    冬
    -0.07
     Cunning
    -0.06
    .accuracy
    -0.06
    .age
    -0.06
     звер
    -0.06
     BUTTON
    -0.06
    ็นการ
    -0.06
     fj
    -0.06
     (%)
    -0.06
    Constant
    -0.06
    POSITIVE LOGITS
     расп
    0.24
     instructional
    0.13
     розп
    0.13
     outbound
    0.09
     Dys
    0.07
    ęd
    0.07
     cửa
    0.07
     sprink
    0.06
    /MPL
    0.06
     anos
    0.06
    Activations Density 0.001%

    No Known Activations