© 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. 128718
    Prev
    Next
    INDEX
    Explanations

    notifications

    np_max-act · gemini-2.0-flash

    software code and programming concepts related to functionality and implementation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on identifiers or method names related to “notification” (e.g. things ending in Notification).

    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
     alın
    -0.07
     recruiters
    -0.07
    lec
    -0.07
     poco
    -0.07
    .Setter
    -0.06
    ниц
    -0.06
     needy
    -0.06
    ctor
    -0.06
    ούν
    -0.06
     Vect
    -0.06
    POSITIVE LOGITS
    -or
    0.07
    detail
    0.06
    “These
    0.06
    \""
    0.06
    	label
    0.06
     lending
    0.06
    -panel
    0.06
     '{
    0.06
    shaft
    0.06
     Begin
    0.06
    Activations Density 0.005%

    No Known Activations