© 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 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. 38992
    Prev
    Next
    INDEX
    Explanations

    testimony

    np_max-act · gemini-2.0-flash

    legal terminology and concepts.

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

    This neuron responds to mentions of witness testimony, detecting words like “testimony,” “testifying,” and related discussion of evidence in legal proceedings.

    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
     smaller
    -0.07
     avoids
    -0.07
    WhatsApp
    -0.07
    -0.07
     bird
    -0.06
     branch
    -0.06
     accelerator
    -0.06
     srp
    -0.06
     创建
    -0.06
    Grid
    -0.06
    POSITIVE LOGITS
     testimony
    0.13
     testify
    0.12
     testim
    0.09
     testified
    0.09
     testimon
    0.08
    ồi
    0.07
    esto
    0.07
     Yani
    0.07
    国内
    0.07
     Say
    0.07
    Activations Density 0.004%

    No Known Activations