© 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. 12394
    Prev
    Next
    INDEX
    Explanations

    Questions/dialogue

    np_max-act · gemini-2.0-flash

    This neuron is effectively “dead” – it never activates on any tokens and doesn’t detect any feature.

    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
    -West
    -0.06
    .Send
    -0.06
    promise
    -0.06
    ereal
    -0.06
    рин
    -0.06
     divine
    -0.06
    .MinValue
    -0.06
     Украї
    -0.06
     panicked
    -0.06
     visiting
    -0.06
    POSITIVE LOGITS
     monoc
    0.07
    IFI
    0.07
     ambush
    0.06
     Element
    0.06
     WARRANTIES
    0.06
     qp
    0.06
    	T
    0.06
    (tree
    0.06
    .')↵
    0.06
     DOS
    0.06
    Activations Density 0.036%

    No Known Activations