© 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. 13665
    Prev
    Next
    INDEX
    Explanations

    Chemistry involving thiols

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the chemical term “thiol” (and its variants) in the text.

    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
    사업
    -0.07
    ニック
    -0.07
    OBJECT
    -0.07
    umped
    -0.07
    닉
    -0.07
    .dropout
    -0.06
    �
    -0.06
    _car
    -0.06
     thất
    -0.06
    咲
    -0.06
    POSITIVE LOGITS
     injecting
    0.07
    σταση
    0.07
     VK
    0.06
     Cond
    0.06
     enjoy
    0.06
     Tipo
    0.06
     featuring
    0.06
     Solution
    0.06
    -counter
    0.06
     Freed
    0.06
    Activations Density 0.002%

    No Known Activations