© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44203
    Prev
    Next
    INDEX
    Explanations

    unrelated topics

    np_max-act · gemini-2.0-flash

    The neuron fires on branded or specialized proper names and technical product titles (e.g. “Photoshop,” “Illustrator,” “Java”).

    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
    シュ
    -0.07
    Width
    -0.07
     Appliances
    -0.06
     XML
    -0.06
     hamstring
    -0.06
     educating
    -0.06
     csv
    -0.06
    acebook
    -0.06
    .rect
    -0.06
    andFilterWhere
    -0.06
    POSITIVE LOGITS
     заклад
    0.07
    atisf
    0.06
     Ост
    0.06
     pudo
    0.06
     ліс
    0.06
     Вони
    0.06
     forte
    0.06
    cult
    0.06
    �
    0.06
    ющего
    0.06
    Activations Density 0.220%

    No Known Activations