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. 125751
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash

    phrases related to song and music promotions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is detecting parts of URLs and link tokens (e.g., “http”, “://”, domain fragments).

    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
     кла
    -0.08
     τά
    -0.07
     bulky
    -0.07
    .build
    -0.07
    Ctl
    -0.06
    ество
    -0.06
    450
    -0.06
    /path
    -0.06
    vides
    -0.06
    CV
    -0.06
    POSITIVE LOGITS
    ,M
    0.07
     dissatisfaction
    0.06
    ordable
    0.06
    мин
    0.06
    /lab
    0.06
    _PRE
    0.06
    -ball
    0.06
     accredited
    0.06
    밀
    0.06
    금
    0.06
    Activations Density 0.024%

    No Known Activations