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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57864
    Prev
    Next
    INDEX
    Explanations

    verbs and processes

    np_max-act · gemini-2.0-flash

    the neuron specializes in spotting procedural action words that describe chemical reaction steps (e.g. “reacted,” “treated,” “purified,” “dissolved,” “subjected”).

    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
    ﾍ
    -0.06
     muc
    -0.06
    ‌کنندگان
    -0.06
    now
    -0.06
    YLE
    -0.06
    toBe
    -0.06
    )size
    -0.06
    /tools
    -0.06
     Lew
    -0.06
    yz
    -0.06
    POSITIVE LOGITS
     него
    0.07
     climb
    0.07
     Rover
    0.06
     لكل
    0.06
    шая
    0.06
     pens
    0.06
     Karachi
    0.06
    conn
    0.06
     SOUND
    0.06
    pcb
    0.06
    Activations Density 0.086%

    No Known Activations