© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13451
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron detects JSON key names and formatting elements (e.g., field labels in quotes and surrounding punctuation).

    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
     Test
    -0.07
    -automatic
    -0.06
     provisioning
    -0.06
    .white
    -0.06
    lig
    -0.06
     motif
    -0.06
     appropriated
    -0.06
    (null
    -0.06
    zimmer
    -0.06
     tie
    -0.06
    POSITIVE LOGITS
    ，存于
    0.07
    <d
    0.07
     ре
    0.06
    -dr
    0.06
    َّ
    0.06
     Sanayi
    0.06
    ΑΜ
    0.06
    َّ
    0.06
     prakt
    0.06
    *i
    0.06
    Activations Density 0.027%

    No Known Activations