© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92183
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash

    phrases related to artificial intelligence and machine learning models.

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

    The main thing this neuron does is spot mentions of NLP tasks or capabilities (e.g. “summarization,” “translation,” “analysis,” “embeddings,” 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
     ponds
    -0.07
    rav
    -0.06
     할
    -0.06
    rdf
    -0.06
     reputed
    -0.06
    主任
    -0.06
     Preserve
    -0.06
     receiving
    -0.06
     +↵
    -0.05
    ("|
    -0.05
    POSITIVE LOGITS
    øj
    0.07
    prm
    0.07
    -added
    0.07
     pornofilm
    0.07
    /Page
    0.07
     Dram
    0.06
    (editor
    0.06
     evolution
    0.06
    _sex
    0.06
    預
    0.06
    Activations Density 0.044%

    No Known Activations