© 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. 6026
    Prev
    Next
    INDEX
    Explanations

    Confidentiality

    np_max-act · gemini-2.0-flash

    content related to investigations and police work.

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find assurances of confidentiality or privacy/security promises.

    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
     endors
    -0.07
     марта
    -0.07
    ckett
    -0.07
    arsity
    -0.07
    casting
    -0.07
    sweet
    -0.07
     şeyler
    -0.06
     solic
    -0.06
     де
    -0.06
     chest
    -0.06
    POSITIVE LOGITS
    翻
    0.06
     userEmail
    0.06
    plevel
    0.06
    exampleModalLabel
    0.06
    _tensor
    0.06
    slots
    0.06
    theValue
    0.06
    IODevice
    0.06
    yssey
    0.06
    MHz
    0.06
    Activations Density 0.060%

    No Known Activations