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. 59327
    Prev
    Next
    INDEX
    Explanations

    part

    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
    çiler
    -0.07
     �
    -0.06
    できます
    -0.06
     tjejer
    -0.06
    	os
    -0.06
     urg
    -0.06
     moet
    -0.06
    MarshalAs
    -0.06
    quantity
    -0.06
    евого
    -0.06
    POSITIVE LOGITS
    .chart
    0.06
    IGNED
    0.06
    VB
    0.06
    ICIAL
    0.06
     persistence
    0.06
    _seek
    0.06
    ुप
    0.06
    .DAY
    0.06
    composer
    0.06
    ONT
    0.06
    Activations Density 0.002%

    No Known Activations