© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31050
    Prev
    Next
    INDEX
    Explanations

    guide

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “guide” (and its morphological variants), i.e. it detects references to guiding mechanisms.

    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
    황
    -0.07
     hätte
    -0.06
     DataRow
    -0.06
    як
    -0.06
    HexString
    -0.06
    -men
    -0.06
    buyer
    -0.06
    ekl
    -0.06
    だから
    -0.05
    irect
    -0.05
    POSITIVE LOGITS
     trainable
    0.07
    	Common
    0.07
    .psi
    0.07
    manage
    0.06
     SORT
    0.06
    entlich
    0.06
     Tomorrow
    0.06
     censorship
    0.06
     اطلاعات
    0.06
     placeholder
    0.06
    Activations Density 0.005%

    No Known Activations