© 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. 73748
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash

    the neuron fires on longer, content-bearing words—especially vivid action or imagery verbs and abstract nouns.

    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
    incinnati
    -0.07
    idades
    -0.06
     Wednesday
    -0.06
    慌
    -0.06
    abort
    -0.06
     Frequently
    -0.06
     correctly
    -0.06
     Tôi
    -0.06
     نیست
    -0.06
    unifu
    -0.06
    POSITIVE LOGITS
     Noir
    0.07
    _make
    0.07
     Endpoint
    0.06
    _phrase
    0.06
     sns
    0.06
    /com
    0.06
    _menu
    0.06
    薄
    0.06
     polym
    0.06
     �
    0.06
    Activations Density 0.027%

    No Known Activations