© 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. 108900
    Prev
    Next
    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash

    The neuron flags past‐tense action words—especially verbs of movement or departure (like “left,” “away,” “entered,” “excused,” etc.).

    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
     antennas
    -0.07
    umbnail
    -0.07
     했다
    -0.07
     skillet
    -0.06
    /autoload
    -0.06
    TableWidgetItem
    -0.06
    .mat
    -0.06
    DOUBLE
    -0.06
     >>=
    -0.06
    .AddComponent
    -0.06
    POSITIVE LOGITS
    ips
    0.07
    uez
    0.07
    dy
    0.07
     festivities
    0.06
     pleasures
    0.06
     Dys
    0.06
    pot
    0.06
     hypocrisy
    0.06
    onen
    0.06
     моз
    0.06
    Activations Density 0.017%

    No Known Activations