© 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. 7110
    Prev
    Next
    INDEX
    Explanations

    article "a"

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the phrase “As a …,” particularly in transitional expressions like “As a result,” “As a consequence,” etc.

    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
    rij
    -0.07
     �
    -0.07
     아직
    -0.06
    _ori
    -0.06
    .did
    -0.06
    preh
    -0.06
    ζη
    -0.06
    からない
    -0.06
     pending
    -0.06
    868
    -0.06
    POSITIVE LOGITS
     Sister
    0.06
     �
    0.06
    ール
    0.06
     adherence
    0.06
     bootloader
    0.06
     a
    0.06
    AEA
    0.06
     facult
    0.06
     Capt
    0.06
    executable
    0.06
    Activations Density 0.016%

    No Known Activations