© 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. 90608
    Prev
    Next
    INDEX
    Explanations

    allergies

    np_max-act · gemini-2.0-flash

    causes and conditions related to oral health issues, particularly gum inflammation and canker sores.

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

    The neuron responds to mentions of allergic or contact‐dermatitis type reactions.

    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
    烈
    -0.07
    ฤศจ
    -0.07
    ioni
    -0.06
    _place
    -0.06
     ничего
    -0.06
    وره
    -0.06
    _DIAG
    -0.06
     đoạn
    -0.06
     ruler
    -0.06
     besten
    -0.06
    POSITIVE LOGITS
     HY
    0.07
    _BP
    0.07
    generic
    0.06
    adaptive
    0.06
     çeşit
    0.06
    ..\
    0.06
     TM
    0.06
     HR
    0.06
     Moderate
    0.06
    "]/
    0.06
    Activations Density 0.006%

    No Known Activations