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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39036
    Prev
    Next
    INDEX
    Explanations

    IF

    np_max-act · gemini-2.0-flash

    specific genes and their associated proteins that play roles in cellular processes and signaling pathways.

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

    The neuron detects mentions of eukaryotic translation initiation factors (e.g. “eIF” followed by a number/letter).

    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
     TG
    -0.07
    _dice
    -0.07
    _CHO
    -0.06
    StackTrace
    -0.06
     رمضان
    -0.06
    Exited
    -0.06
     الجم
    -0.06
     Clinton
    -0.06
     NSS
    -0.06
     اضافه
    -0.06
    POSITIVE LOGITS
     ViewBag
    0.07
    widgets
    0.06
     warfare
    0.06
    
    0.06
    ounding
    0.06
    //$
    0.06
    \)
    0.06
    ４
    0.06
     mattress
    0.06
    ={},
    0.06
    Activations Density 0.025%

    No Known Activations