© 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. 73638
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on French present‐participle verb forms ending in “-ant.”

    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
     IND
    -0.07
     deficits
    -0.07
     amat
    -0.07
    Cr
    -0.06
    सन
    -0.06
     Multip
    -0.06
     multin
    -0.06
    atas
    -0.06
    >You
    -0.06
     Fib
    -0.06
    POSITIVE LOGITS
     Falcons
    0.07
     υπ
    0.06
    ]},
    0.06
     jur
    0.06
    ._
    0.06
    خرج
    0.06
    .pending
    0.06
     Herr
    0.06
    URL
    0.06
     lire
    0.05
    Activations Density 0.017%

    No Known Activations