© 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. 87788
    Prev
    Next
    INDEX
    Explanations

    manufactured components

    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
    peace
    -0.06
    Lewis
    -0.06
     Tags
    -0.06
    /month
    -0.06
    choices
    -0.06
    laps
    -0.06
    	un
    -0.06
    halt
    -0.05
    	f
    -0.05
    rak
    -0.05
    POSITIVE LOGITS
     Samoa
    0.08
     sensible
    0.07
    违
    0.07
     naprost
    0.07
    inent
    0.07
     tôi
    0.07
     корист
    0.07
     indent
    0.07
    .toolStripMenuItem
    0.06
     briefing
    0.06
    Activations Density 0.031%

    No Known Activations