© 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. 91679
    Prev
    Next
    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash

    This neuron detects tokens that are part of C/C++ API names and type identifiers (e.g. parts of function names like wcsncpy, printf, socket, rand, new, wchar_t).

    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
     sonuc
    -0.07
     Khan
    -0.07
     cafe
    -0.07
    alette
    -0.07
     Ко
    -0.07
     Liu
    -0.06
    {/
    -0.06
    	End
    -0.06
    ／
    -0.06
     chanting
    -0.06
    POSITIVE LOGITS
    REG
    0.08
    esel
    0.06
    DateTime
    0.06
    Aggregate
    0.06
     Chamber
    0.06
    айт
    0.06
     Lotus
    0.06
    itors
    0.06
     prevalent
    0.06
    атем
    0.06
    Activations Density 0.004%

    No Known Activations