© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    someone

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “someone” (including its possessive form “someone’s”).

    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
    라도
    -0.06
     haze
    -0.06
     شرایط
    -0.06
    perhaps
    -0.06
    /-
    -0.06
    960
    -0.06
    -ul
    -0.06
    Crystal
    -0.06
    ского
    -0.06
    (Test
    -0.06
    POSITIVE LOGITS
     verbally
    0.07
     rég
    0.06
    isti
    0.06
     personne
    0.06
     phù
    0.06
    accepted
    0.06
     vo
    0.06
    iaomi
    0.06
    getContent
    0.06
     loved
    0.06
    Activations Density 0.018%

    No Known Activations