© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13588
    Prev
    Next
    INDEX
    Explanations

    future tense

    np_max-act · gemini-2.0-flash

    The neuron fires on the modal verb "will," marking future‐tense intent.

    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
    ?(:
    -0.06
    .row
    -0.06
     rozvoj
    -0.06
     LRV
    -0.06
    ø
    -0.06
    ones
    -0.06
    誰
    -0.06
     Nou
    -0.06
    (score
    -0.05
     Lê
    -0.05
    POSITIVE LOGITS
    point
    0.07
    بس
    0.07
    izu
    0.07
    _day
    0.07
     executed
    0.06
     mythology
    0.06
    engine
    0.06
     hudeb
    0.06
    proto
    0.06
     awarded
    0.06
    Activations Density 0.007%

    No Known Activations