Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130449
    Prev
    Next
    INDEX
    Explanations

    rationality/intelligence

    np_max-act · gemini-2.0-flash

    This neuron responds to words and phrases related to reasonableness or sanity (e.g., sense, sane, rational, anyone).

    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
    YPD
    -0.07
    	if
    -0.06
    ملة
    -0.06
    fare
    -0.06
    Έ
    -0.06
    ifs
    -0.06
    丈
    -0.06
     Woods
    -0.06
    killer
    -0.06
    ції
    -0.06
    POSITIVE LOGITS
     ray
    0.07
     christian
    0.07
     어느
    0.07
    [axis
    0.07
     возраст
    0.06
    .Variable
    0.06
     omas
    0.06
    (library
    0.06
     Emb
    0.06
    ecure
    0.06
    Activations Density 0.026%

    No Known Activations