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. 125537
    Prev
    Next
    INDEX
    Explanations

    Words ending in "ing"

    np_max-act · gemini-2.0-flash

    This neuron activates on Polish verb morphemes—especially the infinitive suffix “-ować” and similar verb forms.

    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
     shortcut
    -0.07
    Split
    -0.06
    Negative
    -0.06
    -install
    -0.06
    ٠
    -0.06
     besteht
    -0.06
    ViewControllerAnimated
    -0.06
    Integer
    -0.06
     міс
    -0.06
     Tunnel
    -0.06
    POSITIVE LOGITS
    ensual
    0.07
     match
    0.07
     postpon
    0.07
    ignty
    0.07
    ес
    0.06
     adhere
    0.06
    !");
    0.06
     informace
    0.06
     欧美
    0.06
     BLE
    0.06
    Activations Density 0.044%

    No Known Activations