© 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. 55825
    Prev
    Next
    INDEX
    Explanations

    Period token

    np_max-act · gemini-2.0-flash

    The neuron fires on the period character when used as a decimal point (e.g. in version numbers like “1.0”).

    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
    وید
    -0.07
     smokers
    -0.07
     D
    -0.07
    Fr
    -0.07
     eventual
    -0.07
    ντ
    -0.06
     clad
    -0.06
    854
    -0.06
    .BackColor
    -0.06
     P
    -0.06
    POSITIVE LOGITS
     애
    0.06
     Accom
    0.06
    .Concurrent
    0.06
    шиб
    0.06
     �
    0.06
     Corbyn
    0.06
     pornô
    0.05
    -motion
    0.05
     Medieval
    0.05
    ��
    0.05
    Activations Density 0.001%

    No Known Activations