© 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
    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. 52758
    Prev
    Next
    INDEX
    Explanations

    code

    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
    	default
    -0.07
     humidity
    -0.07
     federally
    -0.07
    高
    -0.06
    RequestId
    -0.06
    _input
    -0.06
    _WRITE
    -0.06
    ling
    -0.06
    스가
    -0.06
     créer
    -0.06
    POSITIVE LOGITS
    ~-~-~-~-
    0.07
     menn
    0.06
     bergen
    0.06
     Reactive
    0.06
    Ge
    0.06
     ::↵
    0.06
     consenting
    0.06
     znaj
    0.06
     відч
    0.06
     dalších
    0.05
    Activations Density 0.194%

    No Known Activations