© 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. 89170
    Prev
    Next
    INDEX
    Explanations

    needs

    np_max-act · gemini-2.0-flash

    The neuron detects words in recommendation qualifiers—specifically terms like “fits,” “needs,” and “budget” in phrases such as “best fits your needs and budget.”

    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
    .Loader
    -0.07
     regulated
    -0.07
    .music
    -0.07
     challeng
    -0.06
    safe
    -0.06
     fungus
    -0.06
     baggage
    -0.06
    .pc
    -0.06
    .ci
    -0.06
     用户
    -0.06
    POSITIVE LOGITS
    Λ
    0.06
     examine
    0.06
    ันท
    0.06
    学生
    0.06
    حات
    0.06
    ndl
    0.06
     зна
    0.06
    Che
    0.05
     обор
    0.05
    [W
    0.05
    Activations Density 0.025%

    No Known Activations