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. 23-RESID-POST-AA
    6. 104680
    Prev
    Next
    INDEX
    Explanations

    shoe/shoes

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (levels
    -0.07
     board
    -0.06
    _BL
    -0.06
    (BuildContext
    -0.06
    eft
    -0.06
     بخش
    -0.06
     counted
    -0.06
     ZZ
    -0.06
    Florida
    -0.06
    もしれない
    -0.06
    POSITIVE LOGITS
    ku
    0.08
     adequate
    0.08
     disillusion
    0.07
     ソ
    0.07
     Preparation
    0.07
    LOCATION
    0.07
    마
    0.06
     نسخه
    0.06
     Shoes
    0.06
     KAR
    0.06
    Activations Density 0.009%

    No Known Activations