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. 3-RESID-POST-AA
    6. 122784
    Prev
    Next
    INDEX
    Explanations

    date

    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
     process
    -0.06
    	un
    -0.06
     diligence
    -0.06
    _common
    -0.06
     stigma
    -0.06
     đời
    -0.06
     halk
    -0.06
     ==(
    -0.06
    her
    -0.06
     processes
    -0.06
    POSITIVE LOGITS
    ケット
    0.07
    ést
    0.07
    _LAT
    0.06
     earned
    0.06
    ROS
    0.06
     fascism
    0.06
     destined
    0.06
     zápas
    0.06
     ssh
    0.06
    OFFSET
    0.06
    Activations Density 0.002%

    No Known Activations