© 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. 44387
    Prev
    Next
    INDEX
    Explanations

    decision

    np_max-act · gemini-2.0-flash

    This neuron responds to words related to formal decisions or rulings (e.g., decide, decision, announce, rule).

    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
     persecution
    -0.07
     genocide
    -0.07
    Л
    -0.06
    ��
    -0.06
    Online
    -0.06
    ikleri
    -0.06
     RAW
    -0.06
    είο
    -0.06
     prefer
    -0.06
     ShoppingCart
    -0.06
    POSITIVE LOGITS
    _sleep
    0.07
    .RELATED
    0.07
    _MINOR
    0.06
    _special
    0.06
    .snp
    0.06
    os
    0.06
     retali
    0.06
     resposta
    0.06
                           ↵
    0.06
    .arch
    0.06
    Activations Density 0.014%

    No Known Activations