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. 122699
    Prev
    Next
    INDEX
    Explanations

    dare

    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
     Kitty
    -0.07
     Guy
    -0.07
     commute
    -0.07
    ,!
    -0.07
     flex
    -0.06
    sembles
    -0.06
    بور
    -0.06
     경기
    -0.06
     append
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ButtonTitles
    0.08
    _Resource
    0.06
    낸
    0.06
    ings
    0.06
    =str
    0.06
    bt
    0.06
    esting
    0.06
    illing
    0.06
     boasted
    0.06
    (program
    0.06
    Activations Density 0.004%

    No Known Activations