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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 85292
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “useful” (as in “it will be useful”) in license‐style boilerplate.

    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
     kidneys
    -0.08
     Can
    -0.07
    Can
    -0.07
     Favorite
    -0.07
     какой
    -0.07
    Добав
    -0.07
     البد
    -0.07
     evento
    -0.07
     Phones
    -0.06
     shields
    -0.06
    POSITIVE LOGITS
    groundColor
    0.07
    ποτε
    0.06
     guideline
    0.06
    ille
    0.06
    殿
    0.06
     locker
    0.06
    ynchronous
    0.06
    ('//*[@
    0.06
     Ре
    0.06
     вив
    0.06
    Activations Density 0.001%

    No Known Activations