© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42728
    Prev
    Next
    INDEX
    Explanations

    string (drilling)

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on mentions of drill‐string and drill‐pipe components or closely related drilling‐equipment terms.

    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
     frags
    -0.06
     landscaping
    -0.06
    ]]↵↵
    -0.06
     Canton
    -0.06
     Afghanistan
    -0.06
     sah
    -0.06
    олод
    -0.06
    _firestore
    -0.06
     Neh
    -0.06
     commander
    -0.06
    POSITIVE LOGITS
    (qu
    0.07
    +b
    0.06
    닝
    0.06
    اطر
    0.06
    버전
    0.06
     overst
    0.06
     み
    0.06
     σει
    0.06
    abytes
    0.06
    azers
    0.06
    Activations Density 0.012%

    No Known Activations