© 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. 76982
    Prev
    Next
    INDEX
    Explanations

    probability/game theory

    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
    (initial
    -0.07
    cura
    -0.06
    .setPassword
    -0.06
    	height
    -0.06
    เคล
    -0.06
     flattened
    -0.06
    ậu
    -0.06
     inhibited
    -0.06
    toString
    -0.06
    clin
    -0.06
    POSITIVE LOGITS
     nivel
    0.07
     none
    0.06
    	inline
    0.06
     Portug
    0.06
     야
    0.06
     Fa
    0.06
     horse
    0.06
    .Rotate
    0.06
     部
    0.06
     STORE
    0.06
    Activations Density 0.016%

    No Known Activations