© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RESID-POST-AA
    11. 95502
    Prev
    Next
    INDEX
    Explanations

    commas and "and"

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     инструмент
    -0.08
    cete
    -0.06
     busted
    -0.06
     irm
    -0.06
    PostExecute
    -0.06
     бух
    -0.06
     Uno
    -0.06
    124
    -0.06
    _legacy
    -0.06
    щей
    -0.06
    POSITIVE LOGITS
    )("
    0.07
    	append
    0.07
     nước
    0.07
     Jing
    0.06
    _INET
    0.06
    .failed
    0.06
    ，对
    0.06
     EditorGUI
    0.06
    	define
    0.06
    oline
    0.06
    Activations Density 0.020%

    No Known Activations