© 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. 88904
    Prev
    Next
    INDEX
    Explanations

    surprise

    np_max-act · gemini-2.0-flash

    This neuron activates on Cyrillic‐script text, effectively detecting Russian words.

    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
    eos
    -0.07
    _heap
    -0.06
    _BACK
    -0.06
    .tail
    -0.06
    empty
    -0.06
    (List
    -0.06
     Wendy
    -0.06
    字
    -0.06
    .order
    -0.06
    Copy
    -0.06
    POSITIVE LOGITS
     τρο
    0.08
    /><
    0.07
    цієн
    0.07
     yatır
    0.06
    process
    0.06
     ин
    0.06
    .setAttribute
    0.06
    })"↵
    0.06
    ecera
    0.06
     priv
    0.06
    Activations Density 0.038%

    No Known Activations