© 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. 41468
    Prev
    Next
    INDEX
    Explanations

    plan/planning

    np_max-act · gemini-2.0-flash

    information related to government and infrastructure projects.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects numerical tokens that include decimal values (i.e. floating-point numbers).

    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
     nouveau
    -0.07
     conjunction
    -0.06
    19
    -0.06
    primir
    -0.06
     فشار
    -0.06
    Had
    -0.06
     Brewing
    -0.06
    (enemy
    -0.06
     Bram
    -0.06
    .Equals
    -0.05
    POSITIVE LOGITS
    -Speed
    0.07
     vmax
    0.07
    -ass
    0.07
    INIT
    0.07
    dma
    0.07
     DHCP
    0.07
    леж
    0.06
    MS
    0.06
    _DEAD
    0.06
     assured
    0.06
    Activations Density 0.124%

    No Known Activations