© 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. 41621
    Prev
    Next
    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals in the text, especially floating-point numbers (decimal values).

    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
     flour
    -0.07
    맹
    -0.07
     rozum
    -0.06
    UpDown
    -0.06
    \Entities
    -0.06
     필요
    -0.06
    appro
    -0.06
     Manip
    -0.06
     uni
    -0.06
    RATION
    -0.06
    POSITIVE LOGITS
    proj
    0.07
    ICLES
    0.07
     porta
    0.07
    (RuntimeObject
    0.06
    otence
    0.06
    inyin
    0.06
    _-_
    0.06
    _cutoff
    0.06
     Originally
    0.06
    chemy
    0.06
    Activations Density 0.095%

    No Known Activations