© 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. 6758
    Prev
    Next
    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash

    This neuron fires on placeholder identifiers (e.g. tokens like “NAME_1”) 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
    .Zip
    -0.08
    Ps
    -0.08
    Deadline
    -0.07
    沿
    -0.07
    Decorator
    -0.07
    Compar
    -0.07
    ας
    -0.07
    ddd
    -0.07
    MV
    -0.07
    .isActive
    -0.07
    POSITIVE LOGITS
    �
    0.06
    !");↵↵
    0.06
    ibNameOrNil
    0.06
    .setForeground
    0.05
     kari
    0.05
     guiActive
    0.05
    ;;↵↵
    0.05
     Mut
    0.05
    .replaceAll
    0.05
    ']];↵
    0.05
    Activations Density 0.096%

    No Known Activations