© 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. 129595
    Prev
    Next
    INDEX
    Explanations

    il

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the French pronoun “il” (especially at the start of impersonal statements), i.e. occurrences of the word “il.”

    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
    8
    -0.07
     Toby
    -0.07
    -free
    -0.06
    芳
    -0.06
    -fed
    -0.06
     подіб
    -0.06
     الخط
    -0.06
     Gotham
    -0.06
    7
    -0.06
     Ampl
    -0.06
    POSITIVE LOGITS
    ];
↵
    0.08
     (?,
    0.07
    };
↵
    0.07
    NotNull
    0.07
    .Hour
    0.07
    گی
    0.07
    'er
    0.07
    े।
    0.07
    (ui
    0.07
    제
    0.07
    Activations Density 0.036%

    No Known Activations