© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6567
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on inline server‐side template expressions (e.g. “<%=…%>” or “<?=…?>”) and URL‐helper calls embedded in markup or script.

    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
     男
    -0.07
     сообщ
    -0.07
    locked
    -0.06
     Wolf
    -0.06
     stanov
    -0.06
     folk
    -0.06
    .Publish
    -0.06
    有关
    -0.06
     ces
    -0.06
     descended
    -0.06
    POSITIVE LOGITS
     contribute
    0.08
    ighting
    0.06
    @extends
    0.06
    	mysqli
    0.06
     spinning
    0.06
     м
    0.06
     могла
    0.06
    》
    0.06
    DA
    0.06
    INIT
    0.06
    Activations Density 0.004%

    No Known Activations