© 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. 13584
    Prev
    Next
    INDEX
    Explanations

    Organizations/Company Names

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of company or organization names (proper noun brand/entity references).

    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
    ư�
    -0.06
    678
    -0.06
    CHK
    -0.06
     tg
    -0.06
    .prop
    -0.06
     �
    -0.06
     obey
    -0.06
    enthal
    -0.06
    Prom
    -0.06
     EMP
    -0.06
    POSITIVE LOGITS
    _component
    0.08
     وضعیت
    0.07
    _lhs
    0.07
     Plugin
    0.06
    孩
    0.06
    .ModelAdmin
    0.06
    的事情
    0.06
    Northern
    0.06
     düşman
    0.06
    .WriteLine
    0.06
    Activations Density 0.120%

    No Known Activations