© 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. 109380
    Prev
    Next
    INDEX
    Explanations

    rop

    np_max-act · gemini-2.0-flash

    references to hadrosaur dinosaurs, including their characteristics, behaviors, and evolutionary significance.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on dinosaur taxonomic names and terms built from the “saur”/“sauropod” root.

    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
    286
    -0.06
    Lat
    -0.06
     �
    -0.06
    627
    -0.06
    _NPC
    -0.06
     Tec
    -0.06
     combating
    -0.06
    365
    -0.06
    625
    -0.06
     고개를
    -0.05
    POSITIVE LOGITS
     findViewById
    0.07
    .Adapter
    0.07
    付け
    0.06
    .horizontal
    0.06
    mutable
    0.06
    (command
    0.06
    addGroup
    0.06
    	num
    0.06
    โซ
    0.06
    .transforms
    0.06
    Activations Density 0.004%

    No Known Activations