Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125669
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron fires on version‐control “Id:” tags in file headers.

    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
     Galactic
    -0.07
     caract
    -0.07
    _EXP
    -0.07
     composers
    -0.06
    _legend
    -0.06
     olmuştur
    -0.06
    Besides
    -0.06
     expansions
    -0.06
     depart
    -0.06
    chten
    -0.06
    POSITIVE LOGITS
     IL
    0.07
    оров
    0.07
    arguments
    0.06
    جات
    0.06
     trusts
    0.06
     đoạn
    0.06
    ,copy
    0.06
    ('').
    0.06
    γραφ
    0.06
    _pixels
    0.06
    Activations Density 0.000%

    No Known Activations