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. 84577
    Prev
    Next
    INDEX
    Explanations

    R dplyr code

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of data‐manipulation pipeline verbs and functions (e.g. group_by, mutate, summarise) typical of dplyr‐style code.

    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
     disabled
    -0.08
    Rem
    -0.07
    Connected
    -0.07
    -banner
    -0.06
    ковий
    -0.06
    เฉล
    -0.06
     boil
    -0.06
     conocer
    -0.06
    -related
    -0.06
    iminary
    -0.06
    POSITIVE LOGITS
     จำก
    0.08
    ardy
    0.07
     pev
    0.07
    uos
    0.06
     +++
    0.06
     BTN
    0.06
    yth
    0.06
    SOR
    0.06
     multip
    0.06
     vyž
    0.06
    Activations Density 0.003%

    No Known Activations