© 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. 44263
    Prev
    Next
    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash

    This neuron fires on C# method declaration keywords (the “private”/“protected” modifiers signaling the start of a method).

    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
     şek
    -0.06
     Sak
    -0.06
     spoke
    -0.06
     Eph
    -0.06
     concentrated
    -0.06
     осуществ
    -0.06
    _buckets
    -0.06
    .data
    -0.06
     oppressed
    -0.06
    .o
    -0.06
    POSITIVE LOGITS
    _VOICE
    0.09
    yıl
    0.07
    _solver
    0.07
    ней
    0.06
     DateTimeOffset
    0.06
    .EMPTY
    0.06
    UNCT
    0.06
     disastr
    0.06
    loops
    0.06
    	private
    0.06
    Activations Density 0.004%

    No Known Activations