© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92433
    Prev
    Next
    INDEX
    Explanations

    website excerpts

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of corporate or product brand names (trademarks).

    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
    FRING
    -0.07
    	StringBuffer
    -0.06
    crease
    -0.06
     Dept
    -0.06
    persistent
    -0.06
     ослож
    -0.06
    .flags
    -0.06
     formulation
    -0.06
     depos
    -0.06
     accelerating
    -0.06
    POSITIVE LOGITS
    -powered
    0.07
    <source
    0.07
    _world
    0.06
     Tech
    0.06
    �
    0.06
    бург
    0.06
    model
    0.06
     Strike
    0.06
    	tests
    0.06
    олод
    0.06
    Activations Density 0.094%

    No Known Activations