© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30699
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    legal terms and references associated with court cases and judicial proceedings.

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

    The neuron picks out numeric tokens—especially floating‐point or decimal numbers as used in statute or citation references.

    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
    。www
    -0.07
    atorium
    -0.06
     materials
    -0.06
    lığın
    -0.06
     önlem
    -0.06
    .apiUrl
    -0.06
    _GENER
    -0.06
    ινό
    -0.06
     لها
    -0.06
     moh
    -0.06
    POSITIVE LOGITS
    .':
    0.07
    –
    0.06
     undergoing
    0.06
     Dispatch
    0.06
    -St
    0.06
     griev
    0.06
     fiss
    0.06
    瓶
    0.06
    asin
    0.06
     sounding
    0.06
    Activations Density 0.004%

    No Known Activations