© 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
    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. 5981
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron flags ordinary assistant “content” words (i.e. the words of the actual answer) as opposed to system tokens or user text.

    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
    visited
    -0.06
     policies
    -0.06
    orient
    -0.06
    bor
    -0.06
    tar
    -0.06
     planning
    -0.06
    istributions
    -0.06
    225
    -0.06
    ullivan
    -0.06
     royal
    -0.06
    POSITIVE LOGITS
    선거
    0.07
     está
    0.07
     aura
    0.07
     keyboardType
    0.07
     tendr
    0.06
    OrNull
    0.06
     生命周期
    0.06
    ulen
    0.06
     Oklahoma
    0.06
    .Encoding
    0.06
    Activations Density 0.044%

    No Known Activations