© 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. 12491
    Prev
    Next
    INDEX
    Explanations

    verify

    np_max-act · gemini-2.0-flash

    technical terms and concepts related to authentication and security protocols.

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

    The neuron activates on words and phrases involved in cryptographic verification (e.g. verify, validate, recalculating signatures, checking integrity).

    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
    _more
    -0.07
    ント
    -0.06
     anche
    -0.06
     stochastic
    -0.06
    _star
    -0.06
     있는
    -0.06
     +"
    -0.06
     UIT
    -0.06
     await
    -0.06
    _FEED
    -0.06
    POSITIVE LOGITS
     Thái
    0.07
     Chiến
    0.07
    екотор
    0.07
    onis
    0.06
     FilePath
    0.06
    _authenticated
    0.06
    iley
    0.06
     accessing
    0.06
     storyboard
    0.06
     Strauss
    0.06
    Activations Density 0.009%

    No Known Activations