© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6404
    Prev
    Next
    INDEX
    Explanations

    orthodox

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the term “Orthodox” (e.g. in “Orthodox Church,” “Eastern Orthodox,” etc.).

    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
    .flag
    -0.08
    595
    -0.07
    215
    -0.07
     Sentence
    -0.07
    });
    -0.07
    Akt
    -0.06
     Captain
    -0.06
    661
    -0.06
     $#
    -0.06
     "").
    -0.06
    POSITIVE LOGITS
     Orthodox
    0.12
     orthodox
    0.10
    odox
    0.07
    odoxy
    0.06
     ort
    0.06
    .labelX
    0.06
    izes
    0.06
    _prom
    0.06
    :NS
    0.06
    ุก
    0.06
    Activations Density 0.001%

    No Known Activations