© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 663
    Prev
    Next
    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash

    This neuron fires on the numerals that introduce or label listicle-style headings (e.g. “10,” “8,” “22,” etc.).

    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
     CGSize
    -0.07
     Fehler
    -0.07
     testCase
    -0.07
    .loaded
    -0.06
    NSAttributedString
    -0.06
     وف
    -0.06
    δες
    -0.06
     daughter
    -0.06
    river
    -0.06
    -controlled
    -0.06
    POSITIVE LOGITS
     explic
    0.06
    crets
    0.06
    manifest
    0.06
    ControlItem
    0.06
     Coupons
    0.06
     zby
    0.06
     organise
    0.06
     incorpor
    0.06
    까지
    0.06
    隠
    0.06
    Activations Density 0.034%

    No Known Activations