© 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. 30949
    Prev
    Next
    INDEX
    Explanations

    Small/minor issues

    np_max-act · gemini-2.0-flash

    The neuron fires on adjectives or adverbs that downplay an issue—i.e. words that flag minor, edge-case, or low-severity problems (like “small,” “rare,” “tiny,” etc.).

    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
    _STEP
    -0.07
    判断
    -0.07
    (is
    -0.06
    LARI
    -0.06
    	id
    -0.06
         	
    -0.06
    ия
    -0.06
    .bitmap
    -0.06
     Jing
    -0.06
    Painter
    -0.06
    POSITIVE LOGITS
     besch
    0.07
     blacklist
    0.07
    Couldn
    0.06
    .addItem
    0.06
    +↵
    0.06
     blev
    0.06
    Loc
    0.06
     Cornel
    0.06
     <%
    0.06
    šky
    0.06
    Activations Density 0.063%

    No Known Activations