© 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
    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. 29640
    Prev
    Next
    INDEX
    Explanations

    Recalls caused by defects

    np_max-act · gemini-2.0-flash

    details regarding product recalls and safety hazards.

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

    The main thing this neuron does is detect language about product defects, malfunctions, recalls, and corrective fixes.

    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
    ea
    -0.07
     tents
    -0.06
     dut
    -0.06
     Ow
    -0.06
     debugging
    -0.06
    Advertising
    -0.06
    duc
    -0.06
     discount
    -0.06
    pat
    -0.06
    IPv
    -0.06
    POSITIVE LOGITS
     getPlayer
    0.07
    )、
    0.07
     labelText
    0.07
     coolest
    0.06
    ☴
    0.06
    ]↵↵
    0.06
     COLL
    0.06
     primeiro
    0.06
     Returned
    0.06
    _Desc
    0.06
    Activations Density 0.027%

    No Known Activations