© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128778
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by demonstrative and discourse‐linking words (e.g. “this,” “these,” “including,” “as”) that introduce or refer back to results or processes.

    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
     hoe
    -0.07
    pri
    -0.07
     arada
    -0.06
    lexical
    -0.06
    _excerpt
    -0.06
    -elements
    -0.06
     showcase
    -0.06
    etypes
    -0.06
    logs
    -0.06
     genomes
    -0.06
    POSITIVE LOGITS
     this
    0.09
     estos
    0.09
     these
    0.08
     faut
    0.07
     THIS
    0.07
     zákaz
    0.06
     возникает
    0.06
     esta
    0.06
    居民
    0.06
     questo
    0.06
    Activations Density 0.189%

    No Known Activations