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

    Neuronpedia

    APICircuit 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. 84546
    Prev
    Next
    INDEX
    Explanations

    news

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the term “news,” i.e. it detects the word “news” in journalistic contexts.

    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
    átní
    -0.09
    flatten
    -0.08
    (Element
    -0.08
     Double
    -0.08
     Někter
    -0.08
    Quant
    -0.07
    IDADE
    -0.07
    .setAttribute
    -0.07
     Turtle
    -0.07
     Dimension
    -0.07
    POSITIVE LOGITS
     News
    0.18
     news
    0.18
    News
    0.12
     NEWS
    0.12
    news
    0.11
    /news
    0.10
    NEWS
    0.09
    -news
    0.09
    .news
    0.09
    (news
    0.09
    Activations Density 0.016%

    No Known Activations