© 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. 68916
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron fires on words listing concrete functional features or components (e.g. “document library,” “calendar,” “discussion board,” “survey”) in a project‐oriented checklist.

    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
    _rp
    -0.07
    [tmp
    -0.06
    %%%%
    -0.06
    (args
    -0.06
    Div
    -0.06
     است
    -0.06
    uing
    -0.06
     initialValues
    -0.06
     بود
    -0.06
     trị
    -0.06
    POSITIVE LOGITS
     بان
    0.06
     contag
    0.06
    ))),↵
    0.06
     COPYRIGHT
    0.06
    _NEAREST
    0.06
     εισ
    0.06
                                                                                       
    0.06
    �
    0.06
     investor
    0.06
    τηγορία
    0.06
    Activations Density 0.089%

    No Known Activations