© 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. 110411
    Prev
    Next
    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    the presence of numeric expressions (e.g. digits, spelled‐out numbers, and durations) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     Haus
    -0.07
    plates
    -0.06
    657
    -0.06
    SMART
    -0.06
     등록
    -0.06
     innocent
    -0.06
     devant
    -0.06
     ponder
    -0.06
    Placement
    -0.06
     plaza
    -0.06
    POSITIVE LOGITS
    _campaign
    0.07
    ß
    0.06
     MCU
    0.06
    andex
    0.06
     polling
    0.06
     Population
    0.06
     ngủ
    0.06
    uitable
    0.06
     -------------
    0.06
    +Sans
    0.05
    Activations Density 0.026%

    No Known Activations