© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126160
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    This neuron detects paper‐size and layout specifications (e.g. “A4,” “Portrait,” “Landscape,” and associated dimension values).

    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
    _plan
    -0.07
     freeze
    -0.07
     работе
    -0.06
    _ENDPOINT
    -0.06
     Einsatz
    -0.06
    .Enums
    -0.06
    +a
    -0.06
     Paradise
    -0.06
    -posts
    -0.06
     Neighbor
    -0.06
    POSITIVE LOGITS
    ิม
    0.06
    يا
    0.06
    _armor
    0.06
    ορ
    0.06
    Modern
    0.06
    それ
    0.06
    opyright
    0.06
    _push
    0.06
    .<
    0.06
    ())){↵
    0.06
    Activations Density 0.002%

    No Known Activations