© 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. 43430
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to the word “end” (and phrases marking the conclusion or final position, like “end of”).

    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
    Ear
    -0.07
    |:
    -0.07
    Founded
    -0.07
    Law
    -0.06
    ав
    -0.06
     lenses
    -0.06
     Kant
    -0.06
    .IsActive
    -0.06
    ±ظ
    -0.06
    ．
    -0.06
    POSITIVE LOGITS
    ظيف
    0.06
    /inc
    0.06
    -comments
    0.06
    .Pro
    0.06
    _parm
    0.06
     начина
    0.06
     possessing
    0.06
    ζει
    0.06
     Penguins
    0.06
     इतन
    0.06
    Activations Density 0.024%

    No Known Activations