© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55596
    Prev
    Next
    INDEX
    Explanations

    substitution

    np_max-act · gemini-2.0-flash

    The neuron activates on words related to replacing something (e.g., “new,” “another,” “replace,” “irreplaceable”).

    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
    epochs
    -0.06
    ってる
    -0.06
    arter
    -0.06
     anticipation
    -0.06
    ("/",
    -0.06
    getID
    -0.06
    슬
    -0.06
    语
    -0.06
     Україна
    -0.06
     tận
    -0.06
    POSITIVE LOGITS
    ;set
    0.08
    BC
    0.07
    esis
    0.07
    (resp
    0.07
     wiki
    0.07
    ertz
    0.07
    _Desc
    0.07
     ↵
    0.06
    	Expect
    0.06
     saya
    0.06
    Activations Density 0.079%

    No Known Activations