© 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. 9148
    Prev
    Next
    INDEX
    Explanations

    dam

    np_max-act · gemini-2.0-flash

    This neuron fires on the initial subword pieces of longer compound or technical words (e.g. “dam,” “bed,” “micro,” “situ,” “coasteer”)—in other words, it detects the beginning segments of multi-morpheme terms.

    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
    .Parcelable
    -0.07
     Explorer
    -0.07
    Ky
    -0.06
    illery
    -0.06
     사이
    -0.06
     pharmaceutical
    -0.06
    >");↵
    -0.06
    �
    -0.06
    Explorer
    -0.06
    UpdatedAt
    -0.06
    POSITIVE LOGITS
     بـ
    0.07
    -org
    0.06
     объяс
    0.06
     πρω
    0.06
     {}).
    0.06
    .CASCADE
    0.06
     stripslashes
    0.06
    /example
    0.06
    arium
    0.06
     �
    0.06
    Activations Density 0.155%

    No Known Activations