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. 19-RESID-POST-AA
    6. 111700
    Prev
    Next
    INDEX
    Explanations

    <

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     swelling
    -0.08
     vad
    -0.07
    heat
    -0.07
     Walking
    -0.06
    !_
    -0.06
    不存在
    -0.06
    	next
    -0.06
     restored
    -0.06
    しまう
    -0.06
     repar
    -0.06
    POSITIVE LOGITS
    )':
    0.07
    ,↵
    0.06
    ّد
    0.06
    .'
    0.06
    ucker
    0.06
    .compiler
    0.06
     развитие
    0.06
                   
    0.06
     Canon
    0.06
     duy
    0.06
    Activations Density 0.015%

    No Known Activations