© 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. 41066
    Prev
    Next
    INDEX
    Explanations

    Punctuation and "and"

    np_max-act · gemini-2.0-flash

    references to events and their organizational aspects within the sports industry.

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

    This neuron activates on words and phrases that appear as part of enumerated lists of offerings or programs (i.e. list items introduced after a colon or in a series).

    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
    ldata
    -0.07
    uning
    -0.06
    beam
    -0.06
    ado
    -0.06
    _dictionary
    -0.06
    .uint
    -0.06
    ured
    -0.06
     セ
    -0.06
     towers
    -0.06
     autof
    -0.06
    POSITIVE LOGITS
     يح
    0.07
     інші
    0.06
     iniciar
    0.06
    LIMIT
    0.06
     tiếp
    0.06
     Follow
    0.06
     Extension
    0.06
    ёр
    0.06
    .FromSeconds
    0.06
    (compare
    0.06
    Activations Density 0.053%

    No Known Activations