© 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. 128724
    Prev
    Next
    INDEX
    Explanations

    code/React props

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of “get_” method calls (i.e. function or accessor names beginning with “get_”).

    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
    性能
    -0.06
    ashboard
    -0.06
    characters
    -0.06
    HCI
    -0.06
     STANDARD
    -0.06
     ICU
    -0.06
    ANDARD
    -0.06
     walkthrough
    -0.06
    ेशक
    -0.06
    commended
    -0.05
    POSITIVE LOGITS
     فل
    0.08
     hindi
    0.07
     amendment
    0.07
    (percent
    0.07
    -foot
    0.07
    (formData
    0.06
     politely
    0.06
    ît
    0.06
    mile
    0.06
     miles
    0.06
    Activations Density 0.022%

    No Known Activations