© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 53667
    Prev
    Next
    INDEX
    Explanations

    trick

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;"><?
    -0.07
     sentiments
    -0.07
     Living
    -0.07
     sense
    -0.07
    енсив
    -0.07
    -being
    -0.06
    bio
    -0.06
     پرداخت
    -0.06
     ><?
    -0.06
     anguish
    -0.06
    POSITIVE LOGITS
     trick
    0.15
     tricks
    0.14
     Trick
    0.13
     Tricks
    0.13
     tricky
    0.10
     Ordering
    0.07
    .C
    0.07
     rigged
    0.07
    Retry
    0.06
    -G
    0.06
    Activations Density 0.005%

    No Known Activations