© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash

    This neuron fires on instructional phrasing that uses the gerund “using” (as in “by using one of the methods…”) to introduce how-to steps.

    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
     음악
    -0.07
    uality
    -0.07
    亿
    -0.06
    Latitude
    -0.06
    gettext
    -0.06
    utron
    -0.06
    %x
    -0.06
    .Cell
    -0.06
    евер
    -0.06
     Pete
    -0.06
    POSITIVE LOGITS
    لان
    0.07
    waiting
    0.07
    dataType
    0.07
     ､
    0.07
    Beans
    0.06
    cke
    0.06
     hind
    0.06
    :none
    0.06
     mně
    0.06
     cust
    0.06
    Activations Density 0.050%

    No Known Activations