© 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. 13441
    Prev
    Next
    INDEX
    Explanations

    programming classes and accessibility

    np_max-act · gemini-2.0-flash

    discussions about access modifiers and their implications in programming, particularly in object-oriented languages.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron triggers on discussion of how class fields or methods can be accessed or modified (e.g. via get/set accessors and access permissions).

    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
    名
    -0.07
    ega
    -0.06
     Alive
    -0.06
    (type
    -0.06
     chipset
    -0.06
    |;↵
    -0.06
     goats
    -0.06
    Acceleration
    -0.06
     psychologists
    -0.05
     implying
    -0.05
    POSITIVE LOGITS
    Makes
    0.08
     kâ
    0.07
    zę
    0.07
    /download
    0.07
     disap
    0.07
    +B
    0.07
    $template
    0.06
     KS
    0.06
    .Min
    0.06
    .Enums
    0.06
    Activations Density 0.011%

    No Known Activations