Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85564
    Prev
    Next
    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting occurrences of the word “party,” especially as part of the compound term “third-party.”

    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
     احمد
    -0.06
     weren
    -0.06
    ListAdapter
    -0.06
    ?.
    -0.06
     deeply
    -0.06
     Caul
    -0.06
     boundaries
    -0.06
     AB
    -0.06
     AG
    -0.06
     було
    -0.06
    POSITIVE LOGITS
    挂
    0.07
    536
    0.07
    صر
    0.07
     and
    0.06
    а
    0.06
    
    0.06
     QName
    0.06
    kill
    0.06
     тро
    0.06
    .args
    0.06
    Activations Density 0.078%

    No Known Activations