© 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. 3-RESID-POST-AA
    11. 93455
    Prev
    Next
    INDEX
    Explanations

    ptr

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     questionnaire
    -0.07
     Filtering
    -0.07
    ining
    -0.06
     QC
    -0.06
     impose
    -0.06
     volume
    -0.06
     characterization
    -0.06
     lider
    -0.06
    (Random
    -0.06
     irradi
    -0.06
    POSITIVE LOGITS
    caption
    0.15
    ochond
    0.10
     systemd
    0.08
     mitochond
    0.08
    oplast
    0.07
    oid
    0.06
    ########
    0.06
     περιοχή
    0.06
    velt
    0.06
    subsection
    0.06
    Activations Density 0.004%

    No Known Activations