© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92564
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash

    This neuron fires on advice or recommendation phrases (e.g. “you should use classes instead,” “an ID is supposed to be unique,” 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
     UITableView
    -0.07
    XObject
    -0.06
     goggles
    -0.06
    ****************************
    -0.06
    .For
    -0.06
    FFT
    -0.06
    ','
    -0.06
    ^\
    -0.06
    usters
    -0.06
    fatal
    -0.06
    POSITIVE LOGITS
     Plants
    0.07
     uzavř
    0.06
    ґ
    0.06
    -resources
    0.06
     관련
    0.06
     복
    0.06
     이런
    0.06
     comenz
    0.06
    ruta
    0.06
    _RES
    0.06
    Activations Density 0.107%

    No Known Activations