© 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. 55764
    Prev
    Next
    INDEX
    Explanations

    Text and code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on digits and numeric expressions (i.e. when the text contains 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
    ,string
    -0.06
     //!
    -0.06
     ate
    -0.06
     Wol
    -0.06
     broth
    -0.05
    _measure
    -0.05
    .Err
    -0.05
    "],["
    -0.05
    	unsigned
    -0.05
     communicates
    -0.05
    POSITIVE LOGITS
    定义
    0.07
    boxing
    0.07
    poons
    0.07
     exceed
    0.07
     キ
    0.07
     streamline
    0.07
    higher
    0.06
    件
    0.06
     treaties
    0.06
     incarcer
    0.06
    Activations Density 0.177%

    No Known Activations