© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87684
    Prev
    Next
    INDEX
    Explanations

    Frustration, repetitive occurrences

    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
    Active
    -0.08
     Bravo
    -0.06
    Jonathan
    -0.06
     IMPLIED
    -0.06
     MULTI
    -0.06
     Rudd
    -0.06
    atis
    -0.06
    Mult
    -0.06
    ート
    -0.06
    yn
    -0.06
    POSITIVE LOGITS
    .readline
    0.07
    _PKT
    0.06
    attachments
    0.06
     birisi
    0.06
    _rel
    0.06
    τικού
    0.06
    (%
    0.06
    	line
    0.06
    */
    0.06
     roy
    0.06
    Activations Density 0.042%

    No Known Activations