© 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. 27-RESID-POST-AA
    11. 56778
    Prev
    Next
    INDEX
    Explanations

    say "ic" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    (dp
    -0.07
     ques
    -0.06
     understood
    -0.06
    XS
    -0.06
     center
    -0.06
     esports
    -0.06
    seq
    -0.06
     quantum
    -0.06
     potatoes
    -0.06
    ++;↵
    -0.06
    POSITIVE LOGITS
     componentDid
    0.07
     गर
    0.07
    Rick
    0.07
    ，由
    0.07
     직접
    0.06
     Donation
    0.06
    OLTIP
    0.06
    Vu
    0.06
    Candidate
    0.06
     Tour
    0.06
    Activations Density 0.001%

    No Known Activations