© 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. 30765
    Prev
    Next
    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash

    structured data in tabular format, specifically key-value pairs.

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

    The neuron responds to numeric tokens and measurement values (e.g. table entries of numbers and units).

    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
    _Statics
    -0.07
     splits
    -0.06
     Dul
    -0.06
    @GeneratedValue
    -0.06
    dance
    -0.06
    _Log
    -0.06
     Morris
    -0.06
     recycling
    -0.06
     understandably
    -0.06
     mammals
    -0.06
    POSITIVE LOGITS
    **(
    0.07
    iselect
    0.07
     bulld
    0.06
    指数
    0.06
    ického
    0.06
     fred
    0.06
    'était
    0.06
    觀
    0.06
     epit
    0.06
    ी.
    0.06
    Activations Density 0.006%

    No Known Activations