© 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. 73805
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens that include a decimal point (i.e. the fractional part of 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
    .cert
    -0.07
    Animated
    -0.07
    ��
    -0.07
    .ma
    -0.06
    -M
    -0.06
     troub
    -0.06
    běh
    -0.06
     چیز
    -0.06
    SX
    -0.06
     Hearts
    -0.06
    POSITIVE LOGITS
     негатив
    0.07
    .Utc
    0.06
     Ав
    0.06
    199
    0.06
    instant
    0.06
    icy
    0.06
    FSIZE
    0.06
    .setId
    0.06
    叫
    0.05
    ':"
    0.05
    Activations Density 0.009%

    No Known Activations