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. 125825
    Prev
    Next
    INDEX
    Explanations

    <%=

    np_max-act · gemini-2.0-flash

    This neuron detects ERB template expressions (the “<%= … %>” interpolation tags) in Rails view code.

    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
    Touch
    -0.08
    ancybox
    -0.08
     targets
    -0.07
    _nodes
    -0.07
    죠
    -0.07
     disasters
    -0.07
     Tactics
    -0.07
     stocked
    -0.07
     Touch
    -0.07
     其他
    -0.07
    POSITIVE LOGITS
     <%=
    0.11
     '<%=
    0.09
    .escape
    0.08
    %=
    0.08
    <?=
    0.07
    de
    0.07
     Elder
    0.07
    ≤
    0.07
    DE
    0.06
    .erase
    0.06
    Activations Density 0.001%

    No Known Activations