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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84394
    Prev
    Next
    INDEX
    Explanations

    27

    np_max-act · gemini-2.0-flash

    The neuron activates on date‐related numeric tokens (e.g. day and month numbers in document timestamps).

    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
    _prev
    -0.07
     fair
    -0.07
     وابسته
    -0.07
     root
    -0.06
     Fair
    -0.06
     incent
    -0.06
    AndWait
    -0.06
     seeding
    -0.06
    /user
    -0.06
    Mapping
    -0.06
    POSITIVE LOGITS
    qq
    0.08
     тер
    0.07
    PullParser
    0.07
    _rewards
    0.07
    (json
    0.06
     dém
    0.06
     Scores
    0.06
     antennas
    0.06
    名称
    0.06
    ewear
    0.06
    Activations Density 0.031%

    No Known Activations