© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 79532
    Prev
    Next
    INDEX
    Explanations

    wound

    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
     freedom
    -0.07
    ('./
    -0.07
     café
    -0.07
     anime
    -0.07
    的一个
    -0.07
    _hours
    -0.07
    _DECLS
    -0.07
    meer
    -0.07
    _HEAP
    -0.07
     layout
    -0.06
    POSITIVE LOGITS
     wounds
    0.15
     wound
    0.13
     wounded
    0.11
     tun
    0.08
    OUND
    0.07
     writ
    0.07
    伤
    0.07
     winds
    0.07
    傷
    0.07
    ウォ
    0.06
    Activations Density 0.004%

    No Known Activations