© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7992
    Prev
    Next
    INDEX
    Explanations

    64

    np_max-act · gemini-2.0-flash

    This neuron never fires on any token in these examples (all activation values are zero), so it effectively does not detect any pattern.

    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
     피
    -0.06
    .EntityFramework
    -0.06
     erfol
    -0.06
     Tro
    -0.06
     enim
    -0.06
     enquiry
    -0.06
     Mel
    -0.06
    .dark
    -0.06
    按钮
    -0.06
     souha
    -0.06
    POSITIVE LOGITS
    _boot
    0.07
     Suarez
    0.07
    …"
    0.07
     (*.
    0.06
    #from
    0.06
    рич
    0.06
    */↵↵↵
    0.06
    DOWN
    0.06
    fer
    0.06
    ��
    0.06
    Activations Density 0.000%

    No Known Activations