© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42850
    Prev
    Next
    INDEX
    Explanations

    originally

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases that introduce a subject’s origin or initial state (e.g. "originally," "initially," "first," "was created").

    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
     Walsh
    -0.06
    _timeout
    -0.06
     unpleasant
    -0.06
    	key
    -0.06
    "When
    -0.06
     experience
    -0.06
     Statistics
    -0.06
     planting
    -0.06
    -breaking
    -0.06
     Robot
    -0.06
    POSITIVE LOGITS
    smarty
    0.07
     مک
    0.07
    elere
    0.07
    RouterModule
    0.07
    [$_
    0.07
    -paced
    0.07
     acompan
    0.07
    ्ग
    0.06
    ges
    0.06
    IFICATE
    0.06
    Activations Density 0.026%

    No Known Activations