© 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. 89876
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron fires on Go’s pointer type indicator (“*”) in type declarations (e.g. “*Redis.Client”, “*bytes.Reader”, etc.).

    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
     películ
    -0.06
     istiyor
    -0.06
    UnitTest
    -0.06
     param
    -0.06
    lış
    -0.06
     "></
    -0.06
    StateChanged
    -0.06
    �
    -0.06
     NSCoder
    -0.06
    ibaba
    -0.06
    POSITIVE LOGITS
    anging
    0.08
     Gear
    0.07
    答
    0.07
     brig
    0.06
     gear
    0.06
    ozo
    0.06
     touring
    0.06
     calendars
    0.06
     Covers
    0.06
     affairs
    0.06
    Activations Density 0.001%

    No Known Activations