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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90408
    Prev
    Next
    INDEX
    Explanations

    phagocytosis

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of “phagocytosis,” i.e. the term (and its subword pieces) describing the phagocytic uptake process.

    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
    猜
    -0.07
    JsonObject
    -0.06
    ,get
    -0.06
    USERNAME
    -0.06
     Müller
    -0.06
     короб
    -0.06
     notebook
    -0.06
    Samples
    -0.06
     زی
    -0.06
     Assessment
    -0.06
    POSITIVE LOGITS
    -pol
    0.07
     oblivious
    0.07
     Coul
    0.06
    	glfw
    0.06
    학년도
    0.06
    ?”
    0.06
     PTS
    0.06
    532
    0.06
     EFF
    0.06
     groupId
    0.06
    Activations Density 0.003%

    No Known Activations