© 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. 55513
    Prev
    Next
    INDEX
    Explanations

    mother

    np_max-act · gemini-2.0-flash

    medical terminology related to patient assessments and respiratory conditions.

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

    The neuron activates on mentions of the (biological) mother or maternal references (e.g., “mother,” “she,” “herself”) in the wet-nurse context.

    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
    ி�
    -0.07
    _regions
    -0.07
    گری
    -0.06
    ERY
    -0.06
     Levi
    -0.06
     داو
    -0.06
    ์ร
    -0.06
    LOUR
    -0.06
    _crop
    -0.06
     Julia
    -0.06
    POSITIVE LOGITS
     continuar
    0.07
                ↵↵
    0.07
    .Identifier
    0.07
     intestinal
    0.07
    "(
    0.06
    +↵↵
    0.06
    packageName
    0.06
    (editor
    0.06
    ा,
    0.06
     spectator
    0.06
    Activations Density 0.061%

    No Known Activations