© 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. 6731
    Prev
    Next
    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on methodological and research-design terms, especially around phrasing of “isolate,” “causal,” “generate,” and “address” when describing study objectives.

    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
    .te
    -0.07
    ALS
    -0.07
     Modifications
    -0.06
     admirable
    -0.06
     içinde
    -0.06
    .fx
    -0.06
    alink
    -0.06
    (mc
    -0.06
     surprises
    -0.06
     Friedman
    -0.06
    POSITIVE LOGITS
     зел
    0.07
     tenía
    0.07
     な
    0.07
    eshire
    0.06
    .Env
    0.06
    ヴァ
    0.06
    .Handler
    0.06
     Бол
    0.06
     。↵
    0.06
    vae
    0.06
    Activations Density 0.151%

    No Known Activations