© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29886
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by the neuter third‐person singular pronoun “it.”

    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
     Alexandre
    -0.06
    ٫
    -0.06
     ")";↵
    -0.06
    طع
    -0.06
     phosphate
    -0.06
    bdd
    -0.06
    ,top
    -0.06
    =',
    -0.06
    Parsing
    -0.06
     -->↵↵
    -0.06
    POSITIVE LOGITS
     it
    0.09
    'It
    0.07
     coloured
    0.07
     It
    0.07
     creado
    0.07
     Pref
    0.06
     notifies
    0.06
     india
    0.06
     undo
    0.06
     advertised
    0.06
    Activations Density 0.093%

    No Known Activations