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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3-RESID-POST-AA
    6. 122861
    Prev
    Next
    INDEX
    Explanations

    uous

    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
     vorhand
    -0.07
     
    
    -0.07
    إن
    -0.07
     onBindViewHolder
    -0.06
     نیست
    -0.06
    lust
    -0.06
    очка
    -0.06
     surtout
    -0.06
    사업
    -0.06
    iêng
    -0.06
    POSITIVE LOGITS
    uous
    0.15
     releg
    0.09
    uously
    0.08
     Clemson
    0.07
    .transition
    0.07
    Transition
    0.07
     waited
    0.07
     Tess
    0.07
    .Linq
    0.07
     Labour
    0.06
    Activations Density 0.001%

    No Known Activations