© 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. 6869
    Prev
    Next
    INDEX
    Explanations

    $$

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any of the shown tokens—it remains inactive, so it isn’t detecting any specific pattern in these excerpts.

    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
    Transient
    -0.07
     
    -0.07
    811
    -0.06
     lecture
    -0.06
    pv
    -0.06
    .TextView
    -0.06
    U
    -0.06
     babys
    -0.06
     influenced
    -0.06
    descricao
    -0.06
    POSITIVE LOGITS
     unite
    0.06
     migrate
    0.06
     срок
    0.06
    цами
    0.06
     创建
    0.06
     брат
    0.06
     ayır
    0.06
     усп
    0.06
    (Container
    0.06
     create
    0.06
    Activations Density 0.016%

    No Known Activations