© 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. 15-RESID-POST-AA
    11. 28904
    Prev
    Next
    INDEX
    Explanations

    overhead

    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
    Negative Logits
    届
    -0.07
    ocaust
    -0.07
     Af
    -0.07
     Across
    -0.07
    时候
    -0.07
    luck
    -0.06
    trap
    -0.06
    -temp
    -0.06
    /article
    -0.06
    Af
    -0.06
    POSITIVE LOGITS
    	node
    0.06
     [<
    0.06
    alon
    0.06
     unreachable
    0.06
     exercising
    0.06
    }.${
    0.06
    .Btn
    0.06
     sk
    0.06
    _namespace
    0.06
    .Custom
    0.06
    Activations Density 0.000%

    No Known Activations