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. 22215
    Prev
    Next
    INDEX
    Explanations

    (

    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
    县
    -0.07
     """
    -0.06
     outing
    -0.06
     Block
    -0.06
    ột
    -0.06
    .single
    -0.06
     Bath
    -0.06
    �
    -0.06
     disputes
    -0.06
     Core
    -0.06
    POSITIVE LOGITS
    abis
    0.07
     dex
    0.06
    ovol
    0.06
     خواست
    0.06
     площад
    0.06
    _camera
    0.06
    lov
    0.06
    (exec
    0.06
    agraph
    0.05
    ucker
    0.05
    Activations Density 0.004%

    No Known Activations