© 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. 109312
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron detects passages containing numerical data—measurements, counts, dates, amounts, or other statistics.

    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
    amus
    -0.07
     unwrap
    -0.07
    속
    -0.07
    .CharField
    -0.06
     медицин
    -0.06
     pavement
    -0.06
    用
    -0.06
    =image
    -0.06
     долго
    -0.06
    -summary
    -0.06
    POSITIVE LOGITS
    _ENC
    0.06
    ATFORM
    0.06
     kidding
    0.06
     donate
    0.06
     Telerik
    0.06
    طال
    0.06
     Сер
    0.06
     footing
    0.06
     Snowden
    0.05
     hedef
    0.05
    Activations Density 0.309%

    No Known Activations