© 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. 42685
    Prev
    Next
    INDEX
    Explanations

    lem

    np_max-act · gemini-2.0-flash

    The neuron is triggered by short, all-caps letter sequences (acronyms or initialisms).

    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
     first
    -0.07
    843
    -0.07
     любой
    -0.07
    1
    -0.07
    agic
    -0.07
    “To
    -0.06
     next
    -0.06
     وارد
    -0.06
    ientras
    -0.06
    ації
    -0.06
    POSITIVE LOGITS
    m
    0.18
    am
    0.17
    om
    0.15
    OM
    0.15
    AM
    0.15
    M
    0.14
    im
    0.14
    em
    0.14
    um
    0.13
    IM
    0.13
    Activations Density 0.938%

    No Known Activations