© 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. 126581
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric quantity tokens (numbers, fractions) and associated measurement words in recipe ingredient lists.

    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
     cultivate
    -0.06
     thresh
    -0.06
     detects
    -0.06
    ičky
    -0.06
    Px
    -0.06
    ��
    -0.06
     nhập
    -0.05
     padx
    -0.05
    bject
    -0.05
    附
    -0.05
    POSITIVE LOGITS
     mocked
    0.07
     assort
    0.07
    :y
    0.06
     Places
    0.06
     battle
    0.06
    _kernel
    0.06
    otros
    0.06
     ότι
    0.06
     tirelessly
    0.06
    toInt
    0.06
    Activations Density 0.018%

    No Known Activations