© 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. 90822
    Prev
    Next
    INDEX
    Explanations

    and as

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the correlative “both … and” construction.

    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
     modest
    -0.06
    Putin
    -0.06
    .timeout
    -0.06
     luc
    -0.06
    cyan
    -0.06
    ζει
    -0.06
     longest
    -0.06
    .Throws
    -0.06
    โป
    -0.06
    ,因为
    -0.06
    POSITIVE LOGITS
    TestMethod
    0.07
    tha
    0.07
     Blazers
    0.06
    ü
    0.06
    jl
    0.06
    £
    0.06
    	params
    0.06
    scri
    0.06
    Upper
    0.06
    Esp
    0.06
    Activations Density 0.031%

    No Known Activations