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. 15-RESID-POST-AA
    6. 74747
    Prev
    Next
    INDEX
    Explanations

    GUID or UUID identifiers

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deadline
    -0.07
    igate
    -0.07
     cleaning
    -0.06
     демон
    -0.06
    olta
    -0.06
    irie
    -0.06
    757
    -0.06
    060
    -0.06
    unning
    -0.06
    (dic
    -0.06
    POSITIVE LOGITS
     favor
    0.06
     Meta
    0.06
    ################################################################
    0.06
     �
    0.06
     Sebast
    0.06
     getName
    0.06
    .Annotations
    0.06
     datasets
    0.06
    _episode
    0.06
    Markdown
    0.06
    Activations Density 0.208%

    No Known Activations