© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91536
    Prev
    Next
    INDEX
    Explanations

    scientific research software

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric values (decimal measurements).

    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
    _SUBJECT
    -0.06
    xB
    -0.06
    adar
    -0.06
    ANDING
    -0.06
     blooms
    -0.06
    벤
    -0.06
     finances
    -0.06
    　　　　　
    -0.06
     excuses
    -0.06
     nové
    -0.06
    POSITIVE LOGITS
     nebo
    0.07
     농
    0.07
    ют
    0.07
    ney
    0.07
    ả
    0.07
    ��
    0.07
    (err
    0.06
     Relative
    0.06
    360
    0.06
     adjusted
    0.06
    Activations Density 0.000%

    No Known Activations