© 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. 44557
    Prev
    Next
    INDEX
    Explanations

    processes, implementation, analysis

    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
     designing
    -0.07
    犯
    -0.07
    _tex
    -0.07
     did
    -0.07
    lications
    -0.07
    ває
    -0.06
     creed
    -0.06
    كيل
    -0.06
    amen
    -0.06
    ξεις
    -0.06
    POSITIVE LOGITS
    _valor
    0.08
    ={!
    0.06
    	sprintf
    0.06
     هفته
    0.06
    ;↵↵↵↵↵
    0.06
     estoy
    0.06
     realmente
    0.06
    ()].
    0.06
    .toLocale
    0.06
     wow
    0.06
    Activations Density 0.064%

    No Known Activations