© 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. 45156
    Prev
    Next
    INDEX
    Explanations

    sentence

    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
    уда
    -0.07
    нев
    -0.07
    )("
    -0.07
    ива
    -0.07
    оке
    -0.06
     našeho
    -0.06
     ker
    -0.06
    oucher
    -0.06
    レット
    -0.06
     surgery
    -0.06
    POSITIVE LOGITS
     witch
    0.06
     dosage
    0.06
     sexist
    0.06
     rsp
    0.06
    	req
    0.06
     Gaga
    0.06
     lemma
    0.06
    _matrices
    0.06
    佳
    0.06
     HttpResponseMessage
    0.06
    Activations Density 0.031%

    No Known Activations