© 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. 74781
    Prev
    Next
    INDEX
    Explanations

    Cut

    np_max-act · gemini-2.0-flash

    expressive statements of strong affection or love.

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

    This neuron detects mentions of crafting tool or brand names (e.g., “Cuttlebug”).

    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
    (auto
    -0.07
    Chat
    -0.07
     deze
    -0.06
    into
    -0.06
    Modes
    -0.06
     tenemos
    -0.06
    \Model
    -0.06
    datatable
    -0.06
     roundup
    -0.06
    .getRequest
    -0.06
    POSITIVE LOGITS
     приня
    0.07
     exhaustion
    0.06
     univerz
    0.06
    HQ
    0.06
     transition
    0.06
    提示
    0.06
     bef
    0.06
     Yatırım
    0.06
     sacrificed
    0.06
     Le
    0.06
    Activations Density 0.000%

    No Known Activations