© 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. 30745
    Prev
    Next
    INDEX
    Explanations

    Technical/Engineering Texts

    np_max-act · gemini-2.0-flash

    This neuron identifies mentions of “men’s” (as in men’s sports teams or similar gendered categories).

    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
     Kens
    -0.07
     Schn
    -0.06
     lyr
    -0.06
     spherical
    -0.06
    ецт
    -0.06
    .fillRect
    -0.06
    PostalCodesNL
    -0.06
     mashed
    -0.06
     bishop
    -0.06
    (database
    -0.05
    POSITIVE LOGITS
    virt
    0.08
    Contin
    0.07
    _NOW
    0.07
    British
    0.07
    	Route
    0.06
    _ag
    0.06
     });↵
    0.06
    Leaf
    0.06
    _INFORMATION
    0.06
    _past
    0.06
    Activations Density 0.876%

    No Known Activations