Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 93260
    Prev
    Next
    INDEX
    Explanations

    eye

    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
     setPassword
    -0.08
     Ihnen
    -0.07
    folders
    -0.07
    _ts
    -0.07
     Callback
    -0.07
     Ideal
    -0.07
    	events
    -0.07
     lxml
    -0.06
     gameState
    -0.06
     Handlers
    -0.06
    POSITIVE LOGITS
     глаз
    0.07
     kararı
    0.06
    �
    0.06
     içindeki
    0.06
     frantic
    0.06
     eyel
    0.06
     Eye
    0.06
     دلیل
    0.06
     dang
    0.06
     reproduced
    0.06
    Activations Density 0.007%

    No Known Activations