© 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. 127366
    Prev
    Next
    INDEX
    Explanations

    to

    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
    یز
    -0.07
     congratulations
    -0.07
    ========
    -0.07
    		 ↵
    -0.06
    .fr
    -0.06
    Congratulations
    -0.06
    finite
    -0.06
    .getMax
    -0.06
     scraps
    -0.06
    ihar
    -0.06
    POSITIVE LOGITS
     ­
    0.06
    (typ
    0.06
     zun
    0.06
     sue
    0.06
    งของ
    0.06
    on
    0.06
     trabal
    0.06
     DA
    0.06
     Im
    0.06
     Exercise
    0.06
    Activations Density 0.025%

    No Known Activations