© 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. 36492
    Prev
    Next
    INDEX
    Explanations

    .

    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
    Negative Logits
     RR
    -0.08
     father
    -0.08
     Aaron
    -0.07
     train
    -0.07
    itur
    -0.07
    .yahoo
    -0.07
     Henry
    -0.07
     عد
    -0.07
     John
    -0.07
    .Profile
    -0.06
    POSITIVE LOGITS
     Ms
    0.13
    Ms
    0.08
     passwd
    0.06
     slime
    0.06
     подс
    0.06
     ".$
    0.06
     niece
    0.06
    	Me
    0.06
    uchsia
    0.06
    yne
    0.06
    Activations Density 0.002%

    No Known Activations