Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110032
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    The neuron fires on quotation‐mark characters that are escaped (e.g. the `\"` sequences or mixed‐quote delimiters) inside string literals.

    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
    막
    -0.07
     trợ
    -0.06
    TO
    -0.06
     tried
    -0.06
     macro
    -0.06
     Graz
    -0.06
     Kara
    -0.06
    _Key
    -0.06
     Legs
    -0.06
     niece
    -0.06
    POSITIVE LOGITS
     Concurrent
    0.07
     concurrent
    0.07
    ,email
    0.07
    objective
    0.06
                        ↵                    ↵
    0.06
    픈
    0.06
                ↵            ↵
    0.06
    ')->
    0.06
    ;",↵
    0.06
    ;;↵↵
    0.06
    Activations Density 0.054%

    No Known Activations