© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129663
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects legal‐procedure phrases specifying appellate standards of review (e.g. “review … for clear error,” “de novo review,” 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
     ship
    -0.08
     باد
    -0.07
    _separator
    -0.07
     graph
    -0.07
    list
    -0.07
    	error
    -0.06
    link
    -0.06
    -list
    -0.06
    LIST
    -0.06
    سته
    -0.06
    POSITIVE LOGITS
    .choices
    0.07
    ewear
    0.07
    契
    0.07
     arising
    0.07
     bestellen
    0.06
     Yüksek
    0.06
    .findIndex
    0.06
     treeNode
    0.06
    ฤด
    0.06
    -floating
    0.06
    Activations Density 0.005%

    No Known Activations