© 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. 43088
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting mixed-case or camelCased identifiers (tokens made of two words joined without spaces).

    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
    /base
    -0.06
    opc
    -0.06
     erh
    -0.06
     Obtain
    -0.06
     Dou
    -0.06
    обав
    -0.06
    تماع
    -0.06
     cứ
    -0.06
     přih
    -0.06
     copy
    -0.06
    POSITIVE LOGITS
     lips
    0.06
    ัดส
    0.06
    .slides
    0.06
     caring
    0.06
    owed
    0.06
     ефектив
    0.06
     india
    0.06
    를
    0.06
    ]<
    0.06
    يلة
    0.06
    Activations Density 0.031%

    No Known Activations