© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126830
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on numeric tokens (especially decimal numbers) in the text.

    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
     males
    -0.06
     marketed
    -0.06
    RN
    -0.06
     suicide
    -0.06
     Fax
    -0.06
    _unsigned
    -0.06
     boxed
    -0.06
    ा�
    -0.06
    �
    -0.06
    Summary
    -0.06
    POSITIVE LOGITS
     Kee
    0.08
     VStack
    0.07
     discriminatory
    0.07
    نگی
    0.07
    (notification
    0.07
     Cly
    0.06
     Что
    0.06
    _ground
    0.06
    نج
    0.06
    Xi
    0.06
    Activations Density 0.002%

    No Known Activations