© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 66614
    Prev
    Next
    INDEX
    Explanations

    Returning to original position

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pik
    -0.07
    iks
    -0.07
    	can
    -0.06
    ue
    -0.06
     della
    -0.06
     diffic
    -0.06
     jmé
    -0.06
     Greg
    -0.06
    nst
    -0.06
    삼
    -0.06
    POSITIVE LOGITS
     undert
    0.07
     nouvelles
    0.06
     SNMP
    0.06
     та
    0.06
    igrations
    0.06
     getP
    0.06
     >>>
    0.06
    cerr
    0.06
    най
    0.06
     UPLOAD
    0.06
    Activations Density 0.049%

    No Known Activations