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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 69054
    Prev
    Next
    INDEX
    Explanations

    source code copyright info

    np_max-act · gemini-2.0-flash

    The neuron fires on capitalized product, project, or library names (e.g. TeleStax, DynamicReports, SpagoBI) typically found in code comments and license headers.

    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
    ’h
    -0.06
     жен
    -0.06
    nímu
    -0.06
    	f
    -0.06
    „A
    -0.06
    pet
    -0.06
    ρίζ
    -0.06
    -rich
    -0.06
     للس
    -0.05
    (script
    -0.05
    POSITIVE LOGITS
    -history
    0.07
    งน
    0.07
     Philippe
    0.07
    parms
    0.06
    .permissions
    0.06
    getElement
    0.06
    十三
    0.06
    ारत
    0.06
     Felix
    0.06
     purge
    0.06
    Activations Density 0.039%

    No Known Activations