© 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. 109442
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on fragments of floating‐point numbers (decimal digits with a dot).

    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
     tặng
    -0.07
     haut
    -0.07
    leaf
    -0.07
    ief
    -0.07
    _ring
    -0.06
    ifix
    -0.06
     flushing
    -0.06
     entrances
    -0.06
    .getMax
    -0.06
     entrance
    -0.06
    POSITIVE LOGITS
     आप
    0.07
     validations
    0.07
     افزار
    0.06
     Others
    0.06
    CancelButton
    0.06
    Advertisement
    0.06
     vuel
    0.06
     Millions
    0.06
     Sql
    0.06
     изменения
    0.06
    Activations Density 0.028%

    No Known Activations