© 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. 76565
    Prev
    Next
    INDEX
    Explanations

    Code or logs

    np_max-act · gemini-2.0-flash

    technical literals in text, especially numeric identifiers and system-style addresses/paths within code or configuration snippets.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     rež
    -0.06
    andas
    -0.06
     mili
    -0.06
    osaur
    -0.06
     muzzle
    -0.06
    Located
    -0.06
     discord
    -0.06
     allies
    -0.06
     purple
    -0.06
    assium
    -0.06
    POSITIVE LOGITS
    nP
    0.07
    isempty
    0.07
    عة
    0.07
    ))?
    0.07
     배열
    0.06
    0.06
     xtype
    0.06
    neck
    0.06
     FUCK
    0.06
    ()+
    0.06
    Activations Density 1.808%

    No Known Activations