© 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. 89541
    Prev
    Next
    INDEX
    Explanations

    bullet points, numbers

    np_max-act · gemini-2.0-flash

    attributes related to qualities and skills important for effective research and data analysis.

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

    This neuron detects numbered list markers (digits and their following punctuation) indicating steps or enumerated items.

    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
    (msg
    -0.07
    PAD
    -0.06
     zombies
    -0.06
    -render
    -0.06
    สภ
    -0.06
    EST
    -0.06
     endure
    -0.06
     сто
    -0.06
     oci
    -0.06
    done
    -0.06
    POSITIVE LOGITS
     linh
    0.07
     (↵↵
    0.07
     excluding
    0.07
    bra
    0.07
    差
    0.07
     Authorization
    0.06
    دهای
    0.06
     Dise
    0.06
     Beetle
    0.06
    -leading
    0.06
    Activations Density 0.049%

    No Known Activations