© 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. 92147
    Prev
    Next
    INDEX
    Explanations

    quality/excellence

    np_max-act · gemini-2.0-flash

    The neuron activates on corporate buzzwords describing a company’s commitments and values (e.g. quality, customer satisfaction, innovation, sustainability, safety).

    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
    NOP
    -0.07
    λου
    -0.07
     contaminated
    -0.07
    炮
    -0.06
     about
    -0.06
    abinet
    -0.06
     Philippine
    -0.06
     imagining
    -0.06
     Hun
    -0.06
     tot
    -0.06
    POSITIVE LOGITS
    очатку
    0.06
     út
    0.06
    _CLOSED
    0.06
    >{{$
    0.06
     IMessage
    0.06
    abwe
    0.06
     nuts
    0.06
    _absolute
    0.06
    ">{{$
    0.06
     Ips
    0.06
    Activations Density 0.032%

    No Known Activations