Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 110304
    Prev
    Next
    INDEX
    Explanations

    starting/trying something

    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
     hàng
    -0.07
    iples
    -0.06
     slows
    -0.06
    lasyon
    -0.06
     přep
    -0.06
    mayı
    -0.06
     grande
    -0.06
     quando
    -0.06
    터
    -0.06
     Planning
    -0.06
    POSITIVE LOGITS
     GURL
    0.07
    (++
    0.07
     Zeit
    0.07
    	pthread
    0.07
     Mapper
    0.06
    [],
    0.06
     ~(
    0.06
    (SDL
    0.06
    (EVENT
    0.06
    etable
    0.06
    Activations Density 0.183%

    No Known Activations