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. 40662
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     політи
    -0.07
     differential
    -0.07
    .ibatis
    -0.07
     habits
    -0.07
    атель
    -0.07
    epar
    -0.06
    ела
    -0.06
    Presence
    -0.06
    	block
    -0.06
     güneş
    -0.06
    POSITIVE LOGITS
    無料
    0.07
    smouth
    0.07
     analogue
    0.06
     purch
    0.06
    -msg
    0.06
    kraine
    0.06
    >To
    0.06
    parison
    0.06
    -rad
    0.06
     anomal
    0.06
    Activations Density 0.101%

    No Known Activations