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. 35824
    Prev
    Next
    INDEX
    Explanations

    Articles

    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
     Enumerable
    -0.08
    :T
    -0.06
    .%
    -0.06
    Encode
    -0.06
    emade
    -0.06
    _catalog
    -0.06
    apixel
    -0.06
    .pan
    -0.06
    ancybox
    -0.06
    _rat
    -0.06
    POSITIVE LOGITS
     La
    0.07
     xe
    0.07
     funkci
    0.06
     修改
    0.06
    (prediction
    0.06
     constitu
    0.06
     yarar
    0.06
     hvis
    0.06
     Loài
    0.06
     COMMON
    0.06
    Activations Density 0.067%

    No Known Activations