© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9286
    Prev
    Next
    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash

    The neuron fires on instances of the reporting verb “report” (as in “we report”) that introduce the main findings in scientific abstracts.

    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
    .geometry
    -0.08
     nối
    -0.07
    jed
    -0.07
     dij
    -0.07
    vertise
    -0.07
    _topology
    -0.07
     punch
    -0.07
    Pure
    -0.06
     connect
    -0.06
     ім
    -0.06
    POSITIVE LOGITS
    .alpha
    0.07
     Fib
    0.06
    flu
    0.06
    아파트
    0.06
    -rate
    0.06
     Vue
    0.06
    账
    0.06
     interim
    0.06
     شکن
    0.06
    -linked
    0.06
    Activations Density 0.015%

    No Known Activations