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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 83451
    Prev
    Next
    INDEX
    Explanations

    arrow

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '.
    -0.07
    "Yeah
    -0.07
     корпус
    -0.07
     Fo
    -0.06
     ".
    -0.06
    Density
    -0.06
    >y
    -0.06
     li
    -0.06
    _board
    -0.06
    cimiento
    -0.06
    POSITIVE LOGITS
     arrow
    0.09
     ------>
    0.08
    ipers
    0.08
    Arrow
    0.07
     arrows
    0.07
     answers
    0.07
    	    		
    0.07
     instructions
    0.07
     probably
    0.06
     advice
    0.06
    Activations Density 0.004%

    No Known Activations