© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92438
    Prev
    Next
    INDEX
    Explanations

    two-letter codes

    np_max-act · gemini-2.0-flash

    This neuron responds to long runs of uppercase letters and digits in certificate-like Base64 blocks (e.g., the body of PEM-encoded certificates).

    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
    683
    -0.07
    لب
    -0.07
    粉
    -0.07
    通知
    -0.07
     wrist
    -0.07
    _rwlock
    -0.07
    _sub
    -0.06
     equalTo
    -0.06
    óż
    -0.06
     giov
    -0.06
    POSITIVE LOGITS
     lessen
    0.07
     Billboard
    0.07
    bone
    0.06
    (tp
    0.06
    /docker
    0.06
     neighbors
    0.06
     faucet
    0.06
    ,target
    0.06
    (bc
    0.06
     explosion
    0.06
    Activations Density 0.005%

    No Known Activations