© 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. 30629
    Prev
    Next
    INDEX
    Explanations

    et

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the “Inet” identifier segment (e.g. the “In” and “et” parts of names like SockaddrInet4/6).

    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
     Manitoba
    -0.06
    763
    -0.06
    (pa
    -0.06
     stavu
    -0.06
    ETwitter
    -0.06
    .setEnabled
    -0.06
    .gray
    -0.06
    شه
    -0.06
    	buf
    -0.06
    getChild
    -0.06
    POSITIVE LOGITS
     systems
    0.07
     giov
    0.07
     Symbols
    0.06
     turnovers
    0.06
     hierarchical
    0.06
     dalam
    0.06
    Argument
    0.06
     desn
    0.06
     �
    0.06
     ail
    0.06
    Activations Density 0.000%

    No Known Activations