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. 50458
    Prev
    Next
    INDEX
    Explanations

    companies and locations

    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
     Labs
    -0.06
     上
    -0.06
     memcmp
    -0.06
     warnings
    -0.06
    .Inner
    -0.06
     �
    -0.06
    ("~
    -0.06
    :$
    -0.06
    ,String
    -0.06
                  
    -0.06
    POSITIVE LOGITS
    agascar
    0.06
    UILDER
    0.06
     H�
    0.06
    �에
    0.06
     Revolution
    0.06
     stare
    0.06
     irgend
    0.06
     uzav
    0.06
    ilit
    0.06
    RED
    0.06
    Activations Density 0.018%

    No Known Activations