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. 11-RESID-POST-AA
    6. 36515
    Prev
    Next
    INDEX
    Explanations

    occasional

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scanning
    -0.07
     Umb
    -0.07
     Kam
    -0.06
     Online
    -0.06
     дослід
    -0.06
     dol
    -0.06
     Jahre
    -0.06
    setValue
    -0.06
    710
    -0.06
     mid
    -0.06
    POSITIVE LOGITS
     disple
    0.07
    enek
    0.07
    스가
    0.07
     stabbed
    0.07
     служби
    0.07
    threat
    0.07
    getRow
    0.06
    inizin
    0.06
    egov
    0.06
    imageView
    0.06
    Activations Density 0.025%

    No Known Activations