© 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. 13067
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical tokens, in particular floating‐point numbers.

    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
    ipmap
    -0.06
    container
    -0.06
    Fault
    -0.06
    chains
    -0.06
    .masks
    -0.06
    -tank
    -0.05
    /ns
    -0.05
     contends
    -0.05
     AK
    -0.05
     вибор
    -0.05
    POSITIVE LOGITS
     decidedly
    0.08
     unmistak
    0.07
     HER
    0.07
    っ�
    0.07
     sodom
    0.07
    °}
    0.06
     mít
    0.06
    <Article
    0.06
     مارس
    0.06
    .InnerException
    0.06
    Activations Density 0.302%

    No Known Activations