© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    rel

    np_max-act · gemini-2.0-flash

    technical terms and concepts related to gravitational theories and their modifications.

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

    This neuron activates on terms naming gravity theories or extensions of general relativity (e.g. “gravity,” “relativity,” “scalar-tensor,” “Brans-Dicke”).

    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
    +Sans
    -0.06
    )”
    -0.06
     screens
    -0.06
     Rohingya
    -0.06
    -shirts
    -0.06
    ilmesi
    -0.06
     pár
    -0.06
    اشة
    -0.06
     Nachricht
    -0.06
    _marshaled
    -0.06
    POSITIVE LOGITS
     os
    0.07
     resolving
    0.07
    591
    0.07
    泣
    0.07
     Automatically
    0.06
     DEAL
    0.06
     cins
    0.06
    _Price
    0.06
    杂
    0.06
     Biom
    0.06
    Activations Density 0.003%

    No Known Activations