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. 27-RESID-POST-AA
    6. 73008
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arctic
    -0.07
    敷
    -0.06
     criticised
    -0.06
     люди
    -0.06
    igation
    -0.06
    Letter
    -0.06
     recursive
    -0.06
     dal
    -0.06
     City
    -0.06
     city
    -0.06
    POSITIVE LOGITS
    期
    0.07
    PerPixel
    0.06
    .we
    0.06
    ailure
    0.06
     happ
    0.06
     TIMESTAMP
    0.06
    %(
    0.06
    ownership
    0.06
     lesen
    0.06
    часно
    0.06
    Activations Density 0.020%

    No Known Activations