© 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. 130019
    Prev
    Next
    INDEX
    Explanations

    indirect

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect words naming specific categories of legal damages (e.g. indirect, incidental, consequential).

    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
     benzer
    -0.07
    "People
    -0.06
    .Public
    -0.06
     lua
    -0.06
    ละเอ
    -0.06
     Seems
    -0.06
    、大
    -0.06
    stance
    -0.06
    _macro
    -0.06
     '"
    -0.06
    POSITIVE LOGITS
    _CLICKED
    0.07
    ]
    0.06
     multicast
    0.06
    ี้↵
    0.06
     :↵↵
    0.06
    _CHILD
    0.06
    =index
    0.06
     ENTITY
    0.06
     Interactive
    0.06
    svg
    0.06
    Activations Density 0.001%

    No Known Activations