© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79401
    Prev
    Next
    INDEX
    Explanations

    ret

    np_max-act · gemini-2.0-flash

    technical terms related to software licensing and rights.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on numeric tokens in source code, in particular on literal constants (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
    λεκ
    -0.06
     NAS
    -0.06
     hizmet
    -0.06
     tasked
    -0.06
    ือด
    -0.06
    _Variable
    -0.06
     мер
    -0.06
    iny
    -0.06
    ENTIAL
    -0.06
    oruč
    -0.06
    POSITIVE LOGITS
     CheckBox
    0.07
     navigator
    0.07
     documentary
    0.06
     δυ
    0.06
    蒙
    0.06
     anyways
    0.06
    dac
    0.06
    투
    0.06
    يا
    0.06
    reactstrap
    0.06
    Activations Density 0.003%

    No Known Activations