© 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. 125091
    Prev
    Next
    INDEX
    Explanations

    u

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of cellular vacuoles or vacuolization in morphological descriptions.

    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
     lối
    -0.07
     Rogers
    -0.07
    Docs
    -0.07
     jsonResponse
    -0.07
     misog
    -0.07
    توان
    -0.06
    _byte
    -0.06
     Treasure
    -0.06
    bble
    -0.06
     ders
    -0.06
    POSITIVE LOGITS
    ิ
    0.07
     Purch
    0.06
    ��
    0.06
     Dual
    0.06
    errals
    0.06
     وال
    0.06
    PREC
    0.06
    /↵↵↵
    0.06
    /"↵↵
    0.06
    (audio
    0.06
    Activations Density 0.001%

    No Known Activations